MushroomRL
dev
API:
Agent-Environment Interface
Actor-Critic
Policy search
Value-Based
Approximators
Distributions
Environments
Features
Policy
Reinforcement Learning utils
Solvers
Utils
Tutorials:
How to make a simple experiment
How to make an advanced experiment
How to create a regressor
How to make a deep RL experiment
How to use the Logger
How to use the Environment interface
How to Save and Load (Serializable interface)
Usage Examples
MushroomRL
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
W
_
__call__() (AbstractGaussianPolicy method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(CategoricalWrapper method)
(ClippedGaussianPolicy method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(EpsGreedy method)
(FourierBasis method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianRBF method)
(GaussianTorchPolicy method)
(LinearParameter method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PolynomialBasis method)
(Preprocessor method)
(Regressor method)
(SGDOptimizer method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TDPolicy method)
(Tiles method)
(TorchPolicy method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(VideoRecorder method)
(VoronoiTiles method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
__init__() (AbstractDQN method)
(AbstractGaussianPolicy method)
(AbstractGridWorld method)
(AccumulatingTrace method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Agent method)
(AgentInfo method)
(AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(Atari method)
(AveragedDQN method)
(BallInACup method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(Box method)
(CarOnHill method)
(CartPole method)
(CategoricalDQN method)
(CategoricalWrapper method)
(ClippedGaussianPolicy method)
(CMAC method)
(ConsoleLogger method)
(COPDAC_Q method)
(Core method)
(CV2Viewer method)
(DataLogger method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Discrete method)
(Distribution method)
(DMControl method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(Environment method)
(EpsGreedy method)
(ExpectedSARSA method)
(FiniteMDP method)
(FourierBasis method)
(FQI method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianRBF method)
(GaussianTorchPolicy method)
(GenericBasisTensor method)
(GPOMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(Habitat method)
(HabitatNavigationWrapper method)
(HabitatRearrangeWrapper method)
(iGibson method)
(ImageViewer method)
(InvertedPendulum method)
(LazyFrames method)
(LinearApproximator method)
(LinearParameter method)
(Logger method)
(LQR method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MDPInfo method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MiniGrid method)
(MinMaxPreprocessor method)
(MuJoCo method)
(MultiMuJoCo method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PolynomialBasis method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(PuddleWorld method)
(PyBullet method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(RandomFourierBasis method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(ReplayMemory method)
(RLearning method)
(RQLearning method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Segway method)
(SequenceReplayMemory method)
(Serializable method)
(SGDOptimizer method)
(ShipSteering method)
(SpeedyQLearning method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(Table method)
(TDPolicy method)
(Tiles method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(VideoRecorder method)
(Viewer method)
(VoronoiTiles method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
_add_save_attr() (AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Agent method)
(AgentInfo method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(CMAC method)
(COPDAC_Q method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GPOMDP method)
(LinearApproximator method)
(LinearParameter method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MDPInfo method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(ReplayMemory method)
(RLearning method)
(RQLearning method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SequenceReplayMemory method)
(Serializable method)
(SGDOptimizer method)
(SpeedyQLearning method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(Table method)
(TDPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
_agent_preprocess() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
_append_folder() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_bound() (AbstractGridWorld static method)
(AirHockeyBase static method)
(AirHockeyBaseBullet static method)
(AirHockeyDefend static method)
(AirHockeyDefendBullet static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyHitBullet static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(AirHockeySingleBullet static method)
(Atari static method)
(BallInACup static method)
(CarOnHill static method)
(CartPole static method)
(DMControl static method)
(Environment static method)
(FiniteMDP static method)
(GridWorld static method)
(GridWorldVanHasselt static method)
(Gym static method)
(Habitat static method)
(iGibson static method)
(InvertedPendulum static method)
(LQR static method)
(MiniGrid static method)
(MuJoCo static method)
(MultiMuJoCo static method)
(PuddleWorld static method)
(PyBullet static method)
(Segway static method)
(ShipSteering static method)
_build_recorder_class() (Core method)
_check_collision() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
_compute() (DecayParameter method)
(LinearParameter method)
(Mellowmax.MellowmaxParameter method)
(Parameter method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
_compute_action() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_compute_exponents() (PolynomialBasis static method)
_compute_gradient() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_convert_to_scale() (GaussianRBFTensor static method)
(GenericBasisTensor static method)
(VonMisesBFTensor static method)
_create_info_dictionary() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
_create_observation() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_custom_load_models() (AirHockeyBaseBullet method)
(AirHockeyDefendBullet method)
(AirHockeyHitBullet method)
(AirHockeySingleBullet method)
(PyBullet method)
_episode_end_update() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_get_collision_force() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
_get_env_id_map() (MultiMuJoCo static method)
_get_serialization_method() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_init_update() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_load_json() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_load_list() (AccumulatingTrace class method)
(AdamOptimizer class method)
(AdaptiveOptimizer class method)
(Optimizer class method)
(ReplacingTrace class method)
(SGDOptimizer class method)
_load_mushroom() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_load_numpy() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_load_pickle() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_load_torch() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_modify_mdp_info() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_modify_observation() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
_next_q() (AbstractDQN method)
(AveragedDQN method)
(CategoricalDQN method)
(DoubleDQN method)
(DQN method)
(DuelingDQN method)
(MaxminDQN method)
(NoisyDQN method)
(QuantileDQN method)
(Rainbow method)
(RQLearning method)
(WeightedQLearning method)
_parse() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_post_load() (AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Agent method)
(AgentInfo method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(CMAC method)
(COPDAC_Q method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GPOMDP method)
(LinearApproximator method)
(LinearParameter method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MDPInfo method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(ReplayMemory method)
(RLearning method)
(RQLearning method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SequenceReplayMemory method)
(Serializable method)
(SGDOptimizer method)
(SpeedyQLearning method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(Table method)
(TDPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
_preprocess() (Core method)
_preprocess_action() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_read_data() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
_reset() (Core method)
_save_json() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_save_mushroom() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_save_numpy() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_save_pickle() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_save_torch() (AccumulatingTrace static method)
(AdamOptimizer static method)
(AdaptiveOptimizer static method)
(Optimizer static method)
(ReplacingTrace static method)
(SGDOptimizer static method)
_simulation_post_step() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_simulation_pre_step() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_step() (Core method)
_step_finalize() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_step_init() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
_step_update() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_update() (DoubleQLearning method)
(ExpectedSARSA method)
(MaxminQLearning method)
(QLambda method)
(QLearning method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
_update_agent_preprocessor() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
_update_parameters() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_update_target() (AbstractDQN method)
(AveragedDQN method)
(CategoricalDQN method)
(DoubleDQN method)
(DQN method)
(DuelingDQN method)
(MaxminDQN method)
(NoisyDQN method)
(QuantileDQN method)
(Rainbow method)
_wait() (CV2Viewer method)
_window_was_closed() (CV2Viewer method)
_write_data() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
A
AbstractDQN (class in mushroom_rl.algorithms.value.dqn)
AbstractGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
AbstractGridWorld (class in mushroom_rl.environments.grid_world)
AccumulatingTrace (class in mushroom_rl.rl_utils.eligibility_trace)
AdamOptimizer (class in mushroom_rl.rl_utils.optimizers)
AdaptiveOptimizer (class in mushroom_rl.rl_utils.optimizers)
add() (PrioritizedReplayMemory method)
(ReplayMemory method)
(SequenceReplayMemory method)
(SumTree method)
add_agent_preprocessor() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
add_core_preprocessor() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
Agent (class in mushroom_rl.core.agent)
AgentInfo (class in mushroom_rl.core.agent)
AirHockeyBase (class in mushroom_rl.environments.mujoco_envs.air_hockey.base)
AirHockeyBaseBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.base)
AirHockeyDefend (class in mushroom_rl.environments.mujoco_envs.air_hockey.defend)
AirHockeyDefendBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.defend)
AirHockeyDouble (class in mushroom_rl.environments.mujoco_envs.air_hockey.double)
AirHockeyHit (class in mushroom_rl.environments.mujoco_envs.air_hockey.hit)
AirHockeyHitBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.hit)
AirHockeyPrepare (class in mushroom_rl.environments.mujoco_envs.air_hockey.prepare)
AirHockeyRepel (class in mushroom_rl.environments.mujoco_envs.air_hockey.repel)
AirHockeySingle (class in mushroom_rl.environments.mujoco_envs.air_hockey.single)
AirHockeySingleBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.single)
arrow_head() (Viewer method)
Atari (class in mushroom_rl.environments.atari)
AveragedDQN (class in mushroom_rl.algorithms.value.dqn)
B
background_image() (Viewer method)
BallInACup (class in mushroom_rl.environments.mujoco_envs.ball_in_a_cup)
bfs() (in module mushroom_rl.solvers.car_on_hill)
Boltzmann (class in mushroom_rl.policy.td_policy)
BoltzmannTorchPolicy (class in mushroom_rl.policy.torch_policy)
BoostedFQI (class in mushroom_rl.algorithms.value.batch_td)
Box (class in mushroom_rl.rl_utils.spaces)
C
CarOnHill (class in mushroom_rl.environments.car_on_hill)
CartPole (class in mushroom_rl.environments.cart_pole)
CategoricalDQN (class in mushroom_rl.algorithms.value.dqn)
CategoricalWrapper (class in mushroom_rl.utils.torch)
circle() (Viewer method)
ClippedGaussianPolicy (class in mushroom_rl.policy.noise_policy)
close() (ImageViewer method)
(Viewer method)
CMAC (class in mushroom_rl.approximators.parametric.cmac)
compute_advantage() (in module mushroom_rl.rl_utils.value_functions)
compute_advantage_montecarlo() (in module mushroom_rl.rl_utils.value_functions)
compute_gae() (in module mushroom_rl.rl_utils.value_functions)
compute_lqr_feedback_gain() (in module mushroom_rl.solvers.lqr)
compute_lqr_P() (in module mushroom_rl.solvers.lqr)
compute_lqr_Q() (in module mushroom_rl.solvers.lqr)
compute_lqr_Q_gaussian_policy() (in module mushroom_rl.solvers.lqr)
compute_lqr_Q_gaussian_policy_gradient_K() (in module mushroom_rl.solvers.lqr)
compute_lqr_V() (in module mushroom_rl.solvers.lqr)
compute_lqr_V_gaussian_policy() (in module mushroom_rl.solvers.lqr)
compute_lqr_V_gaussian_policy_gradient_K() (in module mushroom_rl.solvers.lqr)
compute_mu() (in module mushroom_rl.environments.generators.grid_world)
(in module mushroom_rl.environments.generators.taxi)
compute_probabilities() (in module mushroom_rl.environments.generators.grid_world)
(in module mushroom_rl.environments.generators.simple_chain)
(in module mushroom_rl.environments.generators.taxi)
compute_reward() (in module mushroom_rl.environments.generators.grid_world)
(in module mushroom_rl.environments.generators.simple_chain)
(in module mushroom_rl.environments.generators.taxi)
ConsoleLogger (class in mushroom_rl.core.logger)
ConstantTensor (class in mushroom_rl.features.tensors.constant_tensor)
COPDAC_Q (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
copy() (AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Agent method)
(AgentInfo method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(CMAC method)
(COPDAC_Q method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GPOMDP method)
(LinearApproximator method)
(LinearParameter method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MDPInfo method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(ReplayMemory method)
(RLearning method)
(RQLearning method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SequenceReplayMemory method)
(Serializable method)
(SGDOptimizer method)
(SpeedyQLearning method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(Table method)
(TDPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
Core (class in mushroom_rl.core.core)
core_preprocessors (AbstractDQN property)
(Agent property)
(AveragedDQN property)
(BoostedFQI property)
(CategoricalDQN property)
(COPDAC_Q property)
(DoubleDQN property)
(DoubleFQI property)
(DoubleQLearning property)
(DQN property)
(DuelingDQN property)
(eNAC property)
(ExpectedSARSA property)
(FQI property)
(GPOMDP property)
(LSPI property)
(MaxminDQN property)
(MaxminQLearning property)
(NoisyDQN property)
(QLambda property)
(QLearning property)
(QuantileDQN property)
(Rainbow property)
(REINFORCE property)
(RLearning property)
(RQLearning property)
(SARSA property)
(SARSALambda property)
(SARSALambdaContinuous property)
(SpeedyQLearning property)
(StochasticAC property)
(StochasticAC_AVG property)
(TrueOnlineSARSALambda property)
(WeightedQLearning property)
critical() (ConsoleLogger method)
(Logger method)
CV2Viewer (class in mushroom_rl.utils.viewer)
D
DataLogger (class in mushroom_rl.core.logger)
debug() (ConsoleLogger method)
(Logger method)
DecayParameter (class in mushroom_rl.rl_utils.parameters)
DeterministicPolicy (class in mushroom_rl.policy.deterministic_policy)
DiagonalGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
diff() (AbstractGaussianPolicy method)
(ClippedGaussianPolicy method)
(CMAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(LinearApproximator method)
(NumpyTorchApproximator method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Regressor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TorchApproximator method)
diff_log() (AbstractGaussianPolicy method)
(ClippedGaussianPolicy method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
Discrete (class in mushroom_rl.rl_utils.spaces)
display() (CV2Viewer method)
(ImageViewer method)
(Viewer method)
Distribution (class in mushroom_rl.distributions.distribution)
distribution() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
distribution_t() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
DMControl (class in mushroom_rl.environments.dm_control_env)
DoubleDQN (class in mushroom_rl.algorithms.value.dqn)
DoubleFQI (class in mushroom_rl.algorithms.value.batch_td)
DoubleQLearning (class in mushroom_rl.algorithms.value.td)
DQN (class in mushroom_rl.algorithms.value.dqn)
draw_action() (AbstractDQN method)
(AbstractGaussianPolicy method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(COPDAC_Q method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Policy method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TDPolicy method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
draw_action_t() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
DuelingDQN (class in mushroom_rl.algorithms.value.dqn)
E
EligibilityTrace() (in module mushroom_rl.rl_utils.eligibility_trace)
eNAC (class in mushroom_rl.algorithms.policy_search.policy_gradient)
entropy() (BoltzmannTorchPolicy method)
(Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianTorchPolicy method)
(TorchPolicy method)
entropy_t() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
Environment (class in mushroom_rl.core.environment)
episode_start() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
episode_start_vectorized() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
epoch_info() (ConsoleLogger method)
(Logger method)
EpsGreedy (class in mushroom_rl.policy.td_policy)
error() (ConsoleLogger method)
(Logger method)
euler_to_mat() (in module mushroom_rl.utils.angles)
euler_to_quat() (in module mushroom_rl.utils.angles)
evaluate() (Core method)
exception() (ConsoleLogger method)
(Logger method)
ExpectedSARSA (class in mushroom_rl.algorithms.value.td)
F
Features() (in module mushroom_rl.features.features)
FiniteMDP (class in mushroom_rl.environments.finite_mdp)
fit() (AbstractDQN method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(CMAC method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LinearApproximator method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(Table method)
(TorchApproximator method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
force_arrow() (Viewer method)
FourierBasis (class in mushroom_rl.features.basis.fourier)
FQI (class in mushroom_rl.algorithms.value.batch_td)
function() (Viewer method)
G
GaussianCholeskyDistribution (class in mushroom_rl.distributions.gaussian)
GaussianDiagonalDistribution (class in mushroom_rl.distributions.gaussian)
GaussianDistribution (class in mushroom_rl.distributions.gaussian)
GaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
GaussianRBF (class in mushroom_rl.features.basis.gaussian_rbf)
GaussianRBFTensor (class in mushroom_rl.features.tensors.basis_tensor)
GaussianTorchPolicy (class in mushroom_rl.policy.torch_policy)
generate() (FourierBasis static method)
(GaussianRBF static method)
(GenericBasisTensor class method)
(LQR static method)
(PolynomialBasis static method)
(RandomFourierBasis static method)
(Tiles static method)
(VoronoiTiles static method)
generate_grid_world() (in module mushroom_rl.environments.generators.grid_world)
generate_simple_chain() (in module mushroom_rl.environments.generators.simple_chain)
generate_taxi() (in module mushroom_rl.environments.generators.taxi)
GenericBasisTensor (class in mushroom_rl.features.tensors.basis_tensor)
get() (PrioritizedReplayMemory method)
(ReplayMemory method)
(SequenceReplayMemory method)
(SumTree method)
get_action_features() (in module mushroom_rl.features.features)
get_action_indices() (AirHockeyBase static method)
(AirHockeyDefend static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(BallInACup static method)
(MuJoCo static method)
(MultiMuJoCo static method)
get_action_space() (AirHockeyBase static method)
(AirHockeyDefend static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(BallInACup static method)
(MuJoCo static method)
(MultiMuJoCo static method)
get_all_observation_keys() (AirHockeyBase method)
(AirHockeyDefend method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
get_ee() (AirHockeyDefend method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
get_frame() (Viewer static method)
get_ind() (SumTree method)
get_mean_and_confidence() (in module mushroom_rl.utils.plot)
get_optimal_policy_return() (HabitatNavigationWrapper method)
get_parameters() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
get_puck() (AirHockeyDefend method)
(AirHockeyHit method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
get_q() (Boltzmann method)
(EpsGreedy method)
(Mellowmax method)
(TDPolicy method)
get_regressor() (DeterministicPolicy method)
get_shortest_path() (HabitatNavigationWrapper method)
get_sim_state() (AirHockeyBaseBullet method)
(AirHockeyDefendBullet method)
(AirHockeyHitBullet method)
(AirHockeySingleBullet method)
(PyBullet method)
get_value() (AdaptiveOptimizer method)
(DecayParameter method)
(LinearParameter method)
(Mellowmax.MellowmaxParameter method)
(Parameter method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
get_weights() (AbstractGaussianPolicy method)
(BoltzmannTorchPolicy method)
(ClippedGaussianPolicy method)
(CMAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LinearApproximator method)
(NumpyTorchApproximator method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Regressor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TorchApproximator method)
(TorchPolicy method)
GPOMDP (class in mushroom_rl.algorithms.policy_search.policy_gradient)
GridWorld (class in mushroom_rl.environments.grid_world)
GridWorldVanHasselt (class in mushroom_rl.environments.grid_world)
Gym (class in mushroom_rl.environments.gym_env)
H
Habitat (class in mushroom_rl.environments.habitat_env)
HabitatNavigationWrapper (class in mushroom_rl.environments.habitat_env)
HabitatRearrangeWrapper (class in mushroom_rl.environments.habitat_env)
high (Box property)
I
iGibson (class in mushroom_rl.environments.igibson_env)
ImageViewer (class in mushroom_rl.utils.viewer)
info (AbstractGridWorld property)
(AirHockeyBase property)
(AirHockeyBaseBullet property)
(AirHockeyDefend property)
(AirHockeyDefendBullet property)
(AirHockeyDouble property)
(AirHockeyHit property)
(AirHockeyHitBullet property)
(AirHockeyPrepare property)
(AirHockeyRepel property)
(AirHockeySingle property)
(AirHockeySingleBullet property)
(Atari property)
(BallInACup property)
(CarOnHill property)
(CartPole property)
(DMControl property)
(Environment property)
(FiniteMDP property)
(GridWorld property)
(GridWorldVanHasselt property)
(Gym property)
(Habitat property)
(iGibson property)
(InvertedPendulum property)
(LQR property)
(MiniGrid property)
(MuJoCo property)
(MultiMuJoCo property)
(PuddleWorld property)
(PyBullet property)
(Segway property)
(ShipSteering property)
info() (ConsoleLogger method)
(Logger method)
initial_value (DecayParameter property)
(LinearParameter property)
(Mellowmax.MellowmaxParameter property)
(Parameter property)
(VarianceDecreasingParameter property)
(VarianceIncreasingParameter property)
(VarianceParameter property)
(WindowedVarianceIncreasingParameter property)
(WindowedVarianceParameter property)
initialized (PrioritizedReplayMemory property)
(ReplayMemory property)
(SequenceReplayMemory property)
input_shape (Regressor property)
InvertedPendulum (class in mushroom_rl.environments.inverted_pendulum)
is_absorbing() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
is_cyclic() (GenericBasisTensor class method)
(VonMisesBFTensor class method)
L
LazyFrames (class in mushroom_rl.utils.frames)
learn() (Core method)
line() (Viewer method)
LinearApproximator (class in mushroom_rl.approximators.parametric.linear)
LinearParameter (class in mushroom_rl.rl_utils.parameters)
list_registered() (AbstractGridWorld static method)
(AirHockeyBase static method)
(AirHockeyBaseBullet static method)
(AirHockeyDefend static method)
(AirHockeyDefendBullet static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyHitBullet static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(AirHockeySingleBullet static method)
(Atari static method)
(BallInACup static method)
(CarOnHill static method)
(CartPole static method)
(DMControl static method)
(Environment static method)
(FiniteMDP static method)
(GridWorld static method)
(GridWorldVanHasselt static method)
(Gym static method)
(Habitat static method)
(iGibson static method)
(InvertedPendulum static method)
(LQR static method)
(MiniGrid static method)
(MuJoCo static method)
(MultiMuJoCo static method)
(PuddleWorld static method)
(PyBullet static method)
(Segway static method)
(ShipSteering static method)
load() (AbstractDQN class method)
(AbstractGaussianPolicy class method)
(AccumulatingTrace class method)
(AdamOptimizer class method)
(AdaptiveOptimizer class method)
(Agent class method)
(AgentInfo class method)
(AveragedDQN class method)
(Boltzmann class method)
(BoltzmannTorchPolicy class method)
(BoostedFQI class method)
(CategoricalDQN class method)
(ClippedGaussianPolicy class method)
(CMAC class method)
(COPDAC_Q class method)
(DecayParameter class method)
(DeterministicPolicy class method)
(DiagonalGaussianPolicy class method)
(Distribution class method)
(DoubleDQN class method)
(DoubleFQI class method)
(DoubleQLearning class method)
(DQN class method)
(DuelingDQN class method)
(eNAC class method)
(EpsGreedy class method)
(ExpectedSARSA class method)
(FQI class method)
(GaussianCholeskyDistribution class method)
(GaussianDiagonalDistribution class method)
(GaussianDistribution class method)
(GaussianPolicy class method)
(GaussianTorchPolicy class method)
(GPOMDP class method)
(LinearApproximator class method)
(LinearParameter class method)
(LSPI class method)
(MaxminDQN class method)
(MaxminQLearning class method)
(MDPInfo class method)
(Mellowmax class method)
(Mellowmax.MellowmaxParameter class method)
(MinMaxPreprocessor class method)
(NoisyDQN class method)
(NumpyTorchApproximator class method)
(Optimizer class method)
(OrnsteinUhlenbeckPolicy class method)
(Parameter class method)
(ParametricPolicy class method)
(Policy class method)
(Preprocessor class method)
(PrioritizedReplayMemory class method)
(QLambda class method)
(QLearning class method)
(QuantileDQN class method)
(Rainbow class method)
(Regressor class method)
(REINFORCE class method)
(ReplacingTrace class method)
(ReplayMemory class method)
(RLearning class method)
(RQLearning class method)
(RunningAveragedWindow class method)
(RunningExpWeightedAverage class method)
(RunningStandardization class method)
(SARSA class method)
(SARSALambda class method)
(SARSALambdaContinuous class method)
(SequenceReplayMemory class method)
(Serializable class method)
(SGDOptimizer class method)
(SpeedyQLearning class method)
(StandardizationPreprocessor class method)
(StateLogStdGaussianPolicy class method)
(StateStdGaussianPolicy class method)
(StochasticAC class method)
(StochasticAC_AVG class method)
(SumTree class method)
(Table class method)
(TDPolicy class method)
(TorchApproximator class method)
(TorchPolicy class method)
(TrueOnlineSARSALambda class method)
(VarianceDecreasingParameter class method)
(VarianceIncreasingParameter class method)
(VarianceParameter class method)
(WeightedQLearning class method)
(WindowedVarianceIncreasingParameter class method)
(WindowedVarianceParameter class method)
load_model() (AirHockeyBase static method)
(AirHockeyDefend static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(BallInACup static method)
(MuJoCo static method)
(MultiMuJoCo static method)
load_zip() (AccumulatingTrace class method)
(AdamOptimizer class method)
(AdaptiveOptimizer class method)
(Optimizer class method)
(ReplacingTrace class method)
(SGDOptimizer class method)
log_agent() (DataLogger method)
(Logger method)
log_best_agent() (DataLogger method)
(Logger method)
log_numpy() (DataLogger method)
(Logger method)
log_numpy_array() (DataLogger method)
(Logger method)
log_pdf() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
log_prob_t() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
Logger (class in mushroom_rl.core.logger)
loss_fit (NumpyTorchApproximator property)
(TorchApproximator property)
low (Box property)
LQR (class in mushroom_rl.environments.lqr)
LSPI (class in mushroom_rl.algorithms.value.batch_td)
M
make() (AbstractGridWorld static method)
(AirHockeyBase static method)
(AirHockeyBaseBullet static method)
(AirHockeyDefend static method)
(AirHockeyDefendBullet static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyHitBullet static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(AirHockeySingleBullet static method)
(Atari static method)
(BallInACup static method)
(CarOnHill static method)
(CartPole static method)
(DMControl static method)
(Environment static method)
(FiniteMDP static method)
(GridWorld static method)
(GridWorldVanHasselt static method)
(Gym static method)
(Habitat static method)
(iGibson static method)
(InvertedPendulum static method)
(LQR static method)
(MiniGrid static method)
(MuJoCo static method)
(MultiMuJoCo static method)
(PuddleWorld static method)
(PyBullet static method)
(Segway static method)
(ShipSteering static method)
mat_to_euler() (in module mushroom_rl.utils.angles)
max_p (SumTree property)
max_priority (PrioritizedReplayMemory property)
MaxminDQN (class in mushroom_rl.algorithms.value.dqn)
MaxminQLearning (class in mushroom_rl.algorithms.value.td)
MDPInfo (class in mushroom_rl.core.environment)
mean (RunningAveragedWindow property)
(RunningExpWeightedAverage property)
(RunningStandardization property)
Mellowmax (class in mushroom_rl.policy.td_policy)
Mellowmax.MellowmaxParameter (class in mushroom_rl.policy.td_policy)
minibatch_generator() (in module mushroom_rl.utils.minibatches)
minibatch_number() (in module mushroom_rl.utils.minibatches)
MiniGrid (class in mushroom_rl.environments.minigrid_env)
MinMaxPreprocessor (class in mushroom_rl.rl_utils.preprocessors)
mle() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
model (Regressor property)
module
mushroom_rl.algorithms.actor_critic.classic_actor_critic
mushroom_rl.algorithms.actor_critic.deep_actor_critic
mushroom_rl.algorithms.policy_search.black_box_optimization
mushroom_rl.algorithms.policy_search.policy_gradient
mushroom_rl.algorithms.value.batch_td
mushroom_rl.algorithms.value.dqn
mushroom_rl.algorithms.value.td
mushroom_rl.approximators.parametric.cmac
mushroom_rl.approximators.parametric.linear
mushroom_rl.approximators.parametric.torch_approximator
mushroom_rl.approximators.regressor
mushroom_rl.approximators.table
mushroom_rl.core.agent
mushroom_rl.core.core
mushroom_rl.core.environment
mushroom_rl.core.logger
mushroom_rl.core.serialization
mushroom_rl.distributions.distribution
mushroom_rl.distributions.gaussian
mushroom_rl.environments.car_on_hill
mushroom_rl.environments.cart_pole
mushroom_rl.environments.dm_control_env
mushroom_rl.environments.finite_mdp
mushroom_rl.environments.generators.grid_world
mushroom_rl.environments.generators.simple_chain
mushroom_rl.environments.generators.taxi
mushroom_rl.environments.grid_world
mushroom_rl.environments.gym_env
mushroom_rl.environments.inverted_pendulum
mushroom_rl.environments.lqr
mushroom_rl.environments.minigrid_env
mushroom_rl.environments.mujoco
mushroom_rl.environments.mujoco_envs.air_hockey.base
mushroom_rl.environments.mujoco_envs.air_hockey.defend
mushroom_rl.environments.mujoco_envs.air_hockey.double
mushroom_rl.environments.mujoco_envs.air_hockey.hit
mushroom_rl.environments.mujoco_envs.air_hockey.prepare
mushroom_rl.environments.mujoco_envs.air_hockey.repel
mushroom_rl.environments.mujoco_envs.air_hockey.single
mushroom_rl.environments.mujoco_envs.ball_in_a_cup
mushroom_rl.environments.puddle_world
mushroom_rl.environments.pybullet
mushroom_rl.environments.pybullet_envs.air_hockey.base
mushroom_rl.environments.pybullet_envs.air_hockey.defend
mushroom_rl.environments.pybullet_envs.air_hockey.hit
mushroom_rl.environments.pybullet_envs.air_hockey.single
mushroom_rl.environments.segway
mushroom_rl.environments.ship_steering
mushroom_rl.features._implementations.features_implementation
mushroom_rl.features.basis.fourier
mushroom_rl.features.basis.gaussian_rbf
mushroom_rl.features.basis.polynomial
mushroom_rl.features.features
mushroom_rl.features.tensors.basis_tensor
mushroom_rl.features.tensors.constant_tensor
mushroom_rl.features.tensors.random_fourier_tensor
mushroom_rl.features.tiles.tiles
mushroom_rl.features.tiles.voronoi
mushroom_rl.policy.deterministic_policy
mushroom_rl.policy.gaussian_policy
mushroom_rl.policy.noise_policy
mushroom_rl.policy.policy
mushroom_rl.policy.td_policy
mushroom_rl.policy.torch_policy
mushroom_rl.rl_utils.eligibility_trace
mushroom_rl.rl_utils.optimizers
mushroom_rl.rl_utils.parameters
mushroom_rl.rl_utils.preprocessors
mushroom_rl.rl_utils.replay_memory
mushroom_rl.rl_utils.running_stats
mushroom_rl.rl_utils.spaces
mushroom_rl.rl_utils.value_functions
mushroom_rl.rl_utils.variance_parameters
mushroom_rl.solvers.car_on_hill
mushroom_rl.solvers.dynamic_programming
mushroom_rl.solvers.lqr
mushroom_rl.utils.angles
mushroom_rl.utils.features
mushroom_rl.utils.frames
mushroom_rl.utils.minibatches
mushroom_rl.utils.numerical_gradient
mushroom_rl.utils.plot
mushroom_rl.utils.record
mushroom_rl.utils.torch
mushroom_rl.utils.viewer
MuJoCo (class in mushroom_rl.environments.mujoco)
MultiMuJoCo (class in mushroom_rl.environments.mujoco)
mushroom_rl.algorithms.actor_critic.classic_actor_critic
module
mushroom_rl.algorithms.actor_critic.deep_actor_critic
module
mushroom_rl.algorithms.policy_search.black_box_optimization
module
mushroom_rl.algorithms.policy_search.policy_gradient
module
mushroom_rl.algorithms.value.batch_td
module
mushroom_rl.algorithms.value.dqn
module
mushroom_rl.algorithms.value.td
module
mushroom_rl.approximators.parametric.cmac
module
mushroom_rl.approximators.parametric.linear
module
mushroom_rl.approximators.parametric.torch_approximator
module
mushroom_rl.approximators.regressor
module
mushroom_rl.approximators.table
module
mushroom_rl.core.agent
module
mushroom_rl.core.core
module
mushroom_rl.core.environment
module
mushroom_rl.core.logger
module
mushroom_rl.core.serialization
module
mushroom_rl.distributions.distribution
module
mushroom_rl.distributions.gaussian
module
mushroom_rl.environments.car_on_hill
module
mushroom_rl.environments.cart_pole
module
mushroom_rl.environments.dm_control_env
module
mushroom_rl.environments.finite_mdp
module
mushroom_rl.environments.generators.grid_world
module
mushroom_rl.environments.generators.simple_chain
module
mushroom_rl.environments.generators.taxi
module
mushroom_rl.environments.grid_world
module
mushroom_rl.environments.gym_env
module
mushroom_rl.environments.inverted_pendulum
module
mushroom_rl.environments.lqr
module
mushroom_rl.environments.minigrid_env
module
mushroom_rl.environments.mujoco
module
mushroom_rl.environments.mujoco_envs.air_hockey.base
module
mushroom_rl.environments.mujoco_envs.air_hockey.defend
module
mushroom_rl.environments.mujoco_envs.air_hockey.double
module
mushroom_rl.environments.mujoco_envs.air_hockey.hit
module
mushroom_rl.environments.mujoco_envs.air_hockey.prepare
module
mushroom_rl.environments.mujoco_envs.air_hockey.repel
module
mushroom_rl.environments.mujoco_envs.air_hockey.single
module
mushroom_rl.environments.mujoco_envs.ball_in_a_cup
module
mushroom_rl.environments.puddle_world
module
mushroom_rl.environments.pybullet
module
mushroom_rl.environments.pybullet_envs.air_hockey.base
module
mushroom_rl.environments.pybullet_envs.air_hockey.defend
module
mushroom_rl.environments.pybullet_envs.air_hockey.hit
module
mushroom_rl.environments.pybullet_envs.air_hockey.single
module
mushroom_rl.environments.segway
module
mushroom_rl.environments.ship_steering
module
mushroom_rl.features._implementations.features_implementation
module
mushroom_rl.features.basis.fourier
module
mushroom_rl.features.basis.gaussian_rbf
module
mushroom_rl.features.basis.polynomial
module
mushroom_rl.features.features
module
mushroom_rl.features.tensors.basis_tensor
module
mushroom_rl.features.tensors.constant_tensor
module
mushroom_rl.features.tensors.random_fourier_tensor
module
mushroom_rl.features.tiles.tiles
module
mushroom_rl.features.tiles.voronoi
module
mushroom_rl.policy.deterministic_policy
module
mushroom_rl.policy.gaussian_policy
module
mushroom_rl.policy.noise_policy
module
mushroom_rl.policy.policy
module
mushroom_rl.policy.td_policy
module
mushroom_rl.policy.torch_policy
module
mushroom_rl.rl_utils.eligibility_trace
module
mushroom_rl.rl_utils.optimizers
module
mushroom_rl.rl_utils.parameters
module
mushroom_rl.rl_utils.preprocessors
module
mushroom_rl.rl_utils.replay_memory
module
mushroom_rl.rl_utils.running_stats
module
mushroom_rl.rl_utils.spaces
module
mushroom_rl.rl_utils.value_functions
module
mushroom_rl.rl_utils.variance_parameters
module
mushroom_rl.solvers.car_on_hill
module
mushroom_rl.solvers.dynamic_programming
module
mushroom_rl.solvers.lqr
module
mushroom_rl.utils.angles
module
mushroom_rl.utils.features
module
mushroom_rl.utils.frames
module
mushroom_rl.utils.minibatches
module
mushroom_rl.utils.numerical_gradient
module
mushroom_rl.utils.plot
module
mushroom_rl.utils.record
module
mushroom_rl.utils.torch
module
mushroom_rl.utils.viewer
module
N
n_actions (AccumulatingTrace property)
(ReplacingTrace property)
(Table property)
NoisyDQN (class in mushroom_rl.algorithms.value.dqn)
normalize_angle() (in module mushroom_rl.utils.angles)
normalize_angle_positive() (in module mushroom_rl.utils.angles)
numerical_diff_dist() (in module mushroom_rl.utils.numerical_gradient)
numerical_diff_function() (in module mushroom_rl.utils.numerical_gradient)
numerical_diff_policy() (in module mushroom_rl.utils.numerical_gradient)
NumpyTorchApproximator (class in mushroom_rl.approximators.parametric.torch_approximator)
O
Optimizer (class in mushroom_rl.rl_utils.optimizers)
OrnsteinUhlenbeckPolicy (class in mushroom_rl.policy.noise_policy)
output_shape (Regressor property)
P
Parameter (class in mushroom_rl.rl_utils.parameters)
parameters() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
parameters_size (Distribution property)
(GaussianCholeskyDistribution property)
(GaussianDiagonalDistribution property)
(GaussianDistribution property)
ParametricPolicy (class in mushroom_rl.policy.policy)
parse_grid() (in module mushroom_rl.environments.generators.grid_world)
(in module mushroom_rl.environments.generators.taxi)
path (DataLogger property)
(Logger property)
plot_mean_conf() (in module mushroom_rl.utils.plot)
Policy (class in mushroom_rl.policy.policy)
policy_iteration() (in module mushroom_rl.solvers.dynamic_programming)
polygon() (Viewer method)
PolynomialBasis (class in mushroom_rl.features.basis.polynomial)
predict() (AccumulatingTrace method)
(CMAC method)
(LinearApproximator method)
(NumpyTorchApproximator method)
(Regressor method)
(ReplacingTrace method)
(Table method)
(TorchApproximator method)
preprocess_frame() (in module mushroom_rl.utils.frames)
Preprocessor (class in mushroom_rl.rl_utils.preprocessors)
PrioritizedReplayMemory (class in mushroom_rl.rl_utils.replay_memory)
PuddleWorld (class in mushroom_rl.environments.puddle_world)
PyBullet (class in mushroom_rl.environments.pybullet)
Q
QLambda (class in mushroom_rl.algorithms.value.td)
QLearning (class in mushroom_rl.algorithms.value.td)
QuantileDQN (class in mushroom_rl.algorithms.value.dqn)
quat_to_euler() (in module mushroom_rl.utils.angles)
R
Rainbow (class in mushroom_rl.algorithms.value.dqn)
RandomFourierBasis (class in mushroom_rl.features.tensors.random_fourier_tensor)
register() (AbstractGridWorld class method)
(AirHockeyBase class method)
(AirHockeyBaseBullet class method)
(AirHockeyDefend class method)
(AirHockeyDefendBullet class method)
(AirHockeyDouble class method)
(AirHockeyHit class method)
(AirHockeyHitBullet class method)
(AirHockeyPrepare class method)
(AirHockeyRepel class method)
(AirHockeySingle class method)
(AirHockeySingleBullet class method)
(Atari class method)
(BallInACup class method)
(CarOnHill class method)
(CartPole class method)
(DMControl class method)
(Environment class method)
(FiniteMDP class method)
(GridWorld class method)
(GridWorldVanHasselt class method)
(Gym class method)
(Habitat class method)
(iGibson class method)
(InvertedPendulum class method)
(LQR class method)
(MiniGrid class method)
(MuJoCo class method)
(MultiMuJoCo class method)
(PuddleWorld class method)
(PyBullet class method)
(Segway class method)
(ShipSteering class method)
Regressor (class in mushroom_rl.approximators.regressor)
REINFORCE (class in mushroom_rl.algorithms.policy_search.policy_gradient)
render() (AbstractGridWorld method)
(AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(Atari method)
(BallInACup method)
(CarOnHill method)
(CartPole method)
(DMControl method)
(Environment method)
(FiniteMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(Habitat method)
(iGibson method)
(InvertedPendulum method)
(LQR method)
(MiniGrid method)
(MuJoCo method)
(MultiMuJoCo method)
(PuddleWorld method)
(PyBullet method)
(Segway method)
(ShipSteering method)
ReplacingTrace (class in mushroom_rl.rl_utils.eligibility_trace)
ReplayMemory (class in mushroom_rl.rl_utils.replay_memory)
reset() (AbstractGaussianPolicy method)
(AbstractGridWorld method)
(AccumulatingTrace method)
(AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(Atari method)
(BallInACup method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(CarOnHill method)
(CartPole method)
(ClippedGaussianPolicy method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(DMControl method)
(Environment method)
(EpsGreedy method)
(FiniteMDP method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(Habitat method)
(HabitatNavigationWrapper method)
(HabitatRearrangeWrapper method)
(iGibson method)
(InvertedPendulum method)
(LQR method)
(Mellowmax method)
(MiniGrid method)
(MuJoCo method)
(MultiMuJoCo method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Policy method)
(PuddleWorld method)
(PyBullet method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(Segway method)
(SequenceReplayMemory method)
(ShipSteering method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TDPolicy method)
(TorchPolicy method)
reward() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
RLearning (class in mushroom_rl.algorithms.value.td)
RQLearning (class in mushroom_rl.algorithms.value.td)
RunningAveragedWindow (class in mushroom_rl.rl_utils.running_stats)
RunningExpWeightedAverage (class in mushroom_rl.rl_utils.running_stats)
RunningStandardization (class in mushroom_rl.rl_utils.running_stats)
S
sample() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
SARSA (class in mushroom_rl.algorithms.value.td)
SARSALambda (class in mushroom_rl.algorithms.value.td)
SARSALambdaContinuous (class in mushroom_rl.algorithms.value.td)
save() (AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Agent method)
(AgentInfo method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(CMAC method)
(COPDAC_Q method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GPOMDP method)
(LinearApproximator method)
(LinearParameter method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MDPInfo method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(ReplayMemory method)
(RLearning method)
(RQLearning method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SequenceReplayMemory method)
(Serializable method)
(SGDOptimizer method)
(SpeedyQLearning method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(Table method)
(TDPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
save_zip() (AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(AdamOptimizer method)
(AdaptiveOptimizer method)
(Agent method)
(AgentInfo method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(CMAC method)
(COPDAC_Q method)
(DecayParameter method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GPOMDP method)
(LinearApproximator method)
(LinearParameter method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MDPInfo method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(NoisyDQN method)
(NumpyTorchApproximator method)
(Optimizer method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(ReplacingTrace method)
(ReplayMemory method)
(RLearning method)
(RQLearning method)
(RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SequenceReplayMemory method)
(Serializable method)
(SGDOptimizer method)
(SpeedyQLearning method)
(StandardizationPreprocessor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(Table method)
(TDPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
screen (Viewer property)
seed() (AbstractGridWorld method)
(AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(Atari method)
(BallInACup method)
(CarOnHill method)
(CartPole method)
(DMControl method)
(Environment method)
(FiniteMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(Habitat method)
(iGibson method)
(InvertedPendulum method)
(LQR method)
(MiniGrid method)
(MuJoCo method)
(MultiMuJoCo method)
(PuddleWorld method)
(PyBullet method)
(Segway method)
(ShipSteering method)
Segway (class in mushroom_rl.environments.segway)
SequenceReplayMemory (class in mushroom_rl.rl_utils.replay_memory)
Serializable (class in mushroom_rl.core.serialization)
set_beta() (Boltzmann method)
(Mellowmax method)
set_episode_end() (Atari method)
set_epsilon() (EpsGreedy method)
set_logger() (AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(CategoricalDQN method)
(COPDAC_Q method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(Regressor method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
set_parameters() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
set_q() (Boltzmann method)
(EpsGreedy method)
(Mellowmax method)
(TDPolicy method)
set_sigma() (GaussianPolicy method)
set_std() (DiagonalGaussianPolicy method)
set_weights() (AbstractGaussianPolicy method)
(BoltzmannTorchPolicy method)
(ClippedGaussianPolicy method)
(CMAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LinearApproximator method)
(NumpyTorchApproximator method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Regressor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TorchApproximator method)
(TorchPolicy method)
setup() (AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(BallInACup method)
(MuJoCo method)
(MultiMuJoCo method)
(PyBullet method)
SGDOptimizer (class in mushroom_rl.rl_utils.optimizers)
shape (AccumulatingTrace property)
(Box property)
(DecayParameter property)
(Discrete property)
(LinearParameter property)
(MDPInfo property)
(Mellowmax.MellowmaxParameter property)
(Parameter property)
(ReplacingTrace property)
(Table property)
(VarianceDecreasingParameter property)
(VarianceIncreasingParameter property)
(VarianceParameter property)
(WindowedVarianceIncreasingParameter property)
(WindowedVarianceParameter property)
ShipSteering (class in mushroom_rl.environments.ship_steering)
shortest_angular_distance() (in module mushroom_rl.utils.angles)
size (Discrete property)
(ImageViewer property)
(MDPInfo property)
(ReplayMemory property)
(SequenceReplayMemory property)
(SumTree property)
(Viewer property)
solve_car_on_hill() (in module mushroom_rl.solvers.car_on_hill)
SpeedyQLearning (class in mushroom_rl.algorithms.value.td)
square() (Viewer method)
StandardizationPreprocessor (class in mushroom_rl.rl_utils.preprocessors)
StateLogStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
StateStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
std (RunningStandardization property)
step() (AbstractGridWorld method)
(AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(Atari method)
(BallInACup method)
(CarOnHill method)
(CartPole method)
(DMControl method)
(Environment method)
(FiniteMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(Habitat method)
(HabitatNavigationWrapper method)
(HabitatRearrangeWrapper method)
(iGibson method)
(in module mushroom_rl.solvers.car_on_hill)
(InvertedPendulum method)
(LQR method)
(MiniGrid method)
(MuJoCo method)
(MultiMuJoCo method)
(PuddleWorld method)
(PyBullet method)
(Segway method)
(ShipSteering method)
StochasticAC (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
StochasticAC_AVG (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
stop() (AbstractDQN method)
(AbstractGridWorld method)
(Agent method)
(AirHockeyBase method)
(AirHockeyBaseBullet method)
(AirHockeyDefend method)
(AirHockeyDefendBullet method)
(AirHockeyDouble method)
(AirHockeyHit method)
(AirHockeyHitBullet method)
(AirHockeyPrepare method)
(AirHockeyRepel method)
(AirHockeySingle method)
(AirHockeySingleBullet method)
(Atari method)
(AveragedDQN method)
(BallInACup method)
(BoostedFQI method)
(CarOnHill method)
(CartPole method)
(CategoricalDQN method)
(COPDAC_Q method)
(DMControl method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DQN method)
(DuelingDQN method)
(eNAC method)
(Environment method)
(ExpectedSARSA method)
(FiniteMDP method)
(FQI method)
(GPOMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(Habitat method)
(iGibson method)
(InvertedPendulum method)
(LQR method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MiniGrid method)
(MuJoCo method)
(MultiMuJoCo method)
(NoisyDQN method)
(PuddleWorld method)
(PyBullet method)
(QLambda method)
(QLearning method)
(QuantileDQN method)
(Rainbow method)
(REINFORCE method)
(RLearning method)
(RQLearning method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Segway method)
(ShipSteering method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
strong_line() (ConsoleLogger method)
(Logger method)
SumTree (class in mushroom_rl.rl_utils.replay_memory)
T
Table (class in mushroom_rl.approximators.table)
TDPolicy (class in mushroom_rl.policy.td_policy)
Tiles (class in mushroom_rl.features.tiles.tiles)
TorchApproximator (class in mushroom_rl.approximators.parametric.torch_approximator)
TorchPolicy (class in mushroom_rl.policy.torch_policy)
torque_arrow() (Viewer method)
total_p (SumTree property)
TrueOnlineSARSALambda (class in mushroom_rl.algorithms.value.td)
U
uniform_grid() (in module mushroom_rl.utils.features)
update() (AccumulatingTrace method)
(Boltzmann method)
(DecayParameter method)
(EpsGreedy method)
(LinearParameter method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MinMaxPreprocessor method)
(Parameter method)
(Preprocessor method)
(PrioritizedReplayMemory method)
(ReplacingTrace method)
(StandardizationPreprocessor method)
(SumTree method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
update_stats() (RunningAveragedWindow method)
(RunningExpWeightedAverage method)
(RunningStandardization method)
user_warning_raise_exception() (AirHockeyBase static method)
(AirHockeyDefend static method)
(AirHockeyDouble static method)
(AirHockeyHit static method)
(AirHockeyPrepare static method)
(AirHockeyRepel static method)
(AirHockeySingle static method)
(BallInACup static method)
(MuJoCo static method)
(MultiMuJoCo static method)
V
value_iteration() (in module mushroom_rl.solvers.dynamic_programming)
VarianceDecreasingParameter (class in mushroom_rl.rl_utils.variance_parameters)
VarianceIncreasingParameter (class in mushroom_rl.rl_utils.variance_parameters)
VarianceParameter (class in mushroom_rl.rl_utils.variance_parameters)
VideoRecorder (class in mushroom_rl.utils.record)
Viewer (class in mushroom_rl.utils.viewer)
VonMisesBFTensor (class in mushroom_rl.features.tensors.basis_tensor)
VoronoiTiles (class in mushroom_rl.features.tiles.voronoi)
W
warning() (ConsoleLogger method)
(Logger method)
weak_line() (ConsoleLogger method)
(Logger method)
WeightedQLearning (class in mushroom_rl.algorithms.value.td)
weights_size (AbstractGaussianPolicy property)
(ClippedGaussianPolicy property)
(CMAC property)
(DeterministicPolicy property)
(DiagonalGaussianPolicy property)
(GaussianPolicy property)
(LinearApproximator property)
(NumpyTorchApproximator property)
(OrnsteinUhlenbeckPolicy property)
(ParametricPolicy property)
(Regressor property)
(StateLogStdGaussianPolicy property)
(StateStdGaussianPolicy property)
(TorchApproximator property)
WindowedVarianceIncreasingParameter (class in mushroom_rl.rl_utils.variance_parameters)
WindowedVarianceParameter (class in mushroom_rl.rl_utils.variance_parameters)
Read the Docs
v: dev
Versions
latest
1.7.0
1.5.3
1.4.0
1.3.0
1.2.0
1.1
dev
Downloads
On Read the Docs
Project Home
Builds