MushroomRL
1.7.0
API:
Agent-Environment Interface
Actor-Critic
Policy search
Value-Based
Approximators
Distributions
Environments
Features
Policy
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 use the Serializable interface
MushroomRL
Docs
»
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
|
Z
_
__call__() (AbstractGaussianPolicy method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(Callback method)
(ClippedGaussianPolicy method)
(CollectDataset method)
(CollectMaxQ method)
(CollectParameters method)
(CollectQ method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(EpsGreedy method)
(ExponentialParameter method)
(FourierBasis method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianRBF method)
(GaussianTorchPolicy method)
(LinearParameter method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(OrnsteinUhlenbeckPolicy method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PolynomialBasis method)
(Regressor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TDPolicy method)
(Tiles method)
(TorchPolicy method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(VoronoiTiles method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
__init__ (AbstractGaussianPolicy attribute)
(Distribution attribute)
(ParametricPolicy attribute)
(Policy attribute)
(Serializable attribute)
__init__() (A2C method)
(AbstractDQN method)
(AbstractGridWorld method)
(AccumulatingTrace method)
(Agent method)
(Atari method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(Box method)
(COPDAC_Q method)
(Callback method)
(CarOnHill method)
(CartPole method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(CollectMaxQ method)
(CollectParameters method)
(CollectQ method)
(ConsoleLogger method)
(ConstrainedREPS method)
(Core method)
(DDPG method)
(DMControl method)
(DQN method)
(DataLogger method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Discrete method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(Environment method)
(EpsGreedy method)
(ExpectedSARSA method)
(ExponentialParameter method)
(FQI method)
(FiniteMDP method)
(FourierBasis method)
(GPOMDP method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianRBF method)
(GaussianRBFTensor method)
(GaussianTorchPolicy method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(ImageViewer method)
(InvertedPendulum method)
(LQR method)
(LSPI method)
(LazyFrames method)
(LinearApproximator method)
(LinearParameter method)
(Logger method)
(MDPInfo method)
(MaxAndSkip method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(MuJoCo method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(Parameter method)
(PolynomialBasis method)
(PrioritizedReplayMemory method)
(PuddleWorld method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Segway method)
(ShipSteering method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(SumTree method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(Table method)
(Tiles method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(Viewer method)
(VoronoiTiles method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
(eNAC method)
_add_save_attr() (A2C method)
(AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(EpsGreedy method)
(ExpectedSARSA method)
(ExponentialParameter method)
(FQI method)
(GPOMDP method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LSPI method)
(LinearApproximator method)
(LinearParameter method)
(MDPInfo method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Serializable method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(Table method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
(eNAC method)
_append_folder() (AccumulatingTrace static method)
(ReplacingTrace static method)
_bound() (AbstractGridWorld static method)
(Atari 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)
(InvertedPendulum static method)
(LQR static method)
(MuJoCo static method)
(PuddleWorld static method)
(Segway static method)
(ShipSteering static method)
_check_collision() (MuJoCo method)
_compute() (ExponentialParameter method)
(LinearParameter method)
(Mellowmax.MellowmaxParameter method)
(Parameter method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
_compute_action() (MuJoCo method)
_compute_exponents() (PolynomialBasis static method)
_compute_gradient() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_episode_end_update() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_get_collision_force() (MuJoCo method)
_get_serialization_method() (AccumulatingTrace static method)
(ReplacingTrace static method)
_init_update() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_is_absorbing() (MuJoCo method)
_load_json() (AccumulatingTrace static method)
(ReplacingTrace static method)
_load_list() (mushroom_rl.utils.eligibility_trace.AccumulatingTrace class method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace class method)
_load_mushroom() (AccumulatingTrace static method)
(ReplacingTrace static method)
_load_numpy() (AccumulatingTrace static method)
(ReplacingTrace static method)
_load_pickle() (AccumulatingTrace static method)
(ReplacingTrace static method)
_load_simulation() (MuJoCo method)
_load_torch() (AccumulatingTrace static method)
(ReplacingTrace static method)
_next_q() (AbstractDQN method)
(AveragedDQN method)
(CategoricalDQN method)
(DDPG method)
(DQN method)
(DoubleDQN method)
(DuelingDQN method)
(MaxminDQN method)
(NoisyDQN method)
(RQLearning method)
(Rainbow method)
(SAC method)
(TD3 method)
(WeightedQLearning method)
_optimize_actor_parameters() (A2C method)
(DDPG method)
(DeepAC method)
(SAC method)
(TD3 method)
_parse() (DoubleQLearning static method)
(ExpectedSARSA static method)
(GPOMDP method)
(MaxminQLearning static method)
(QLambda static method)
(QLearning static method)
(REINFORCE method)
(RLearning static method)
(RQLearning static method)
(SARSA static method)
(SARSALambda static method)
(SARSALambdaContinuous static method)
(SpeedyQLearning static method)
(TrueOnlineSARSALambda static method)
(WeightedQLearning static method)
(eNAC method)
_post_load() (A2C method)
(AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(EpsGreedy method)
(ExpectedSARSA method)
(ExponentialParameter method)
(FQI method)
(GPOMDP method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LSPI method)
(LinearApproximator method)
(LinearParameter method)
(MDPInfo method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Serializable method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(Table method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
(eNAC method)
_preprocess() (Core method)
_preprocess_action() (MuJoCo method)
_read_data() (MuJoCo method)
_reward() (MuJoCo method)
_save_json() (AccumulatingTrace static method)
(ReplacingTrace static method)
_save_mushroom() (AccumulatingTrace static method)
(ReplacingTrace static method)
_save_numpy() (AccumulatingTrace static method)
(ReplacingTrace static method)
_save_pickle() (AccumulatingTrace static method)
(ReplacingTrace static method)
_save_torch() (AccumulatingTrace static method)
(ReplacingTrace static method)
_setup() (MuJoCo method)
_simulation_post_step() (MuJoCo method)
_simulation_pre_step() (MuJoCo method)
_step() (Core method)
_step_finalize() (MuJoCo method)
_step_init() (MuJoCo method)
_step_update() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_update() (ConstrainedREPS method)
(DoubleQLearning method)
(ExpectedSARSA method)
(MaxminQLearning method)
(PGPE method)
(QLambda method)
(QLearning method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
_update_parameters() (eNAC method)
(GPOMDP method)
(REINFORCE method)
_update_target() (AbstractDQN method)
(AveragedDQN method)
(CategoricalDQN method)
(DQN method)
(DoubleDQN method)
(DuelingDQN method)
(MaxminDQN method)
(NoisyDQN method)
(Rainbow method)
_write_data() (MuJoCo method)
A
A2C (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
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.utils.eligibility_trace)
add() (PrioritizedReplayMemory method)
(ReplayMemory method)
(SumTree method)
Agent (class in mushroom_rl.core.agent)
arrays_as_dataset() (in module mushroom_rl.utils.dataset)
arrow_head() (Viewer method)
Atari (class in mushroom_rl.environments.atari)
AveragedDQN (class in mushroom_rl.algorithms.value.dqn)
B
background_image() (Viewer method)
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.utils.spaces)
C
Callback (class in mushroom_rl.utils.callbacks)
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)
circle() (Viewer method)
clean() (Callback method)
ClippedGaussianPolicy (class in mushroom_rl.policy.noise_policy)
close() (MaxAndSkip method)
(Viewer method)
CollectDataset (class in mushroom_rl.utils.callbacks)
CollectMaxQ (class in mushroom_rl.utils.callbacks)
CollectParameters (class in mushroom_rl.utils.callbacks)
CollectQ (class in mushroom_rl.utils.callbacks)
compute_advantage() (in module mushroom_rl.utils.value_functions)
compute_advantage_montecarlo() (in module mushroom_rl.utils.value_functions)
compute_gae() (in module mushroom_rl.utils.value_functions)
compute_J() (in module mushroom_rl.utils.dataset)
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_metrics() (in module mushroom_rl.utils.dataset)
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)
ConstrainedREPS (class in mushroom_rl.algorithms.policy_search.black_box_optimization)
COPDAC_Q (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
copy() (A2C method)
(AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(EpsGreedy method)
(ExpectedSARSA method)
(ExponentialParameter method)
(FQI method)
(GPOMDP method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LSPI method)
(LinearApproximator method)
(LinearParameter method)
(MDPInfo method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Serializable method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(Table method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
(eNAC method)
Core (class in mushroom_rl.core.core)
critical() (ConsoleLogger method)
(Logger method)
D
DataLogger (class in mushroom_rl.core.logger)
DDPG (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
debug() (ConsoleLogger method)
(Logger method)
DeepAC (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
DeterministicPolicy (class in mushroom_rl.policy.deterministic_policy)
DiagonalGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
diff() (AbstractGaussianPolicy method)
(ClippedGaussianPolicy method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(LinearApproximator 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.utils.spaces)
display() (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() (A2C method)
(AbstractDQN method)
(AbstractGaussianPolicy method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EpsGreedy method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(ParametricPolicy method)
(Policy method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
(eNAC method)
draw_action_t() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
DuelingDQN (class in mushroom_rl.algorithms.value.dqn)
E
EligibilityTrace() (in module mushroom_rl.utils.eligibility_trace)
eNAC (class in mushroom_rl.algorithms.policy_search.policy_gradient)
EnsembleTable (class in mushroom_rl.utils.table)
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() (A2C method)
(AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(PGPE method)
(PPO method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TRPO method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
(eNAC method)
episodes_length() (in module mushroom_rl.utils.dataset)
epoch_info() (ConsoleLogger method)
(Logger method)
EpsGreedy (class in mushroom_rl.policy.td_policy)
error() (ConsoleLogger method)
(Logger method)
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)
ExponentialParameter (class in mushroom_rl.utils.parameters)
F
Features() (in module mushroom_rl.features.features)
FiniteMDP (class in mushroom_rl.environments.finite_mdp)
fit() (A2C method)
(AbstractDQN method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(LinearApproximator method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(PGPE method)
(PPO method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TRPO method)
(Table method)
(TorchApproximator method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
(eNAC method)
force_arrow() (Viewer method)
force_symlink() (in module mushroom_rl.utils.folder)
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.gaussian_tensor)
GaussianTorchPolicy (class in mushroom_rl.policy.torch_policy)
generate() (FourierBasis static method)
(GaussianRBF static method)
(GaussianRBFTensor static method)
(LQR static method)
(PolynomialBasis 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)
get() (Callback method)
(PrioritizedReplayMemory method)
(ReplayMemory method)
(SumTree method)
get_action_features() (in module mushroom_rl.features.features)
get_gradient() (in module mushroom_rl.utils.torch)
get_parameters() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
get_q() (Boltzmann method)
(EpsGreedy method)
(Mellowmax method)
(TDPolicy method)
get_regressor() (DeterministicPolicy method)
get_value() (ExponentialParameter 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)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LinearApproximator method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Regressor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(in module mushroom_rl.utils.torch)
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
high (Box attribute)
I
ImageViewer (class in mushroom_rl.utils.viewer)
info (AbstractGridWorld attribute)
(Atari attribute)
(CarOnHill attribute)
(CartPole attribute)
(DMControl attribute)
(Environment attribute)
(FiniteMDP attribute)
(GridWorld attribute)
(GridWorldVanHasselt attribute)
(Gym attribute)
(InvertedPendulum attribute)
(LQR attribute)
(MuJoCo attribute)
(PuddleWorld attribute)
(Segway attribute)
(ShipSteering attribute)
info() (ConsoleLogger method)
(Logger method)
initial_value (ExponentialParameter attribute)
(LinearParameter attribute)
(Mellowmax.MellowmaxParameter attribute)
(Parameter attribute)
(VarianceDecreasingParameter attribute)
(VarianceIncreasingParameter attribute)
(VarianceParameter attribute)
(WindowedVarianceIncreasingParameter attribute)
(WindowedVarianceParameter attribute)
initialized (PrioritizedReplayMemory attribute)
(ReplayMemory attribute)
input_shape (Regressor attribute)
InvertedPendulum (class in mushroom_rl.environments.inverted_pendulum)
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.utils.parameters)
list_registered() (AbstractGridWorld static method)
(Atari 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)
(InvertedPendulum static method)
(LQR static method)
(MuJoCo static method)
(PuddleWorld static method)
(Segway static method)
(ShipSteering static method)
load() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q class method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC class method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 class method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO class method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.ConstrainedREPS class method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE class method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS class method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR class method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP class method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE class method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC class method)
(mushroom_rl.algorithms.value.batch_td.BoostedFQI class method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI class method)
(mushroom_rl.algorithms.value.batch_td.FQI class method)
(mushroom_rl.algorithms.value.batch_td.LSPI class method)
(mushroom_rl.algorithms.value.dqn.AbstractDQN class method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN class method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN class method)
(mushroom_rl.algorithms.value.dqn.DQN class method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN class method)
(mushroom_rl.algorithms.value.dqn.DuelingDQN class method)
(mushroom_rl.algorithms.value.dqn.MaxminDQN class method)
(mushroom_rl.algorithms.value.dqn.NoisyDQN class method)
(mushroom_rl.algorithms.value.dqn.Rainbow class method)
(mushroom_rl.algorithms.value.td.DoubleQLearning class method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA class method)
(mushroom_rl.algorithms.value.td.MaxminQLearning class method)
(mushroom_rl.algorithms.value.td.QLambda class method)
(mushroom_rl.algorithms.value.td.QLearning class method)
(mushroom_rl.algorithms.value.td.RLearning class method)
(mushroom_rl.algorithms.value.td.RQLearning class method)
(mushroom_rl.algorithms.value.td.SARSA class method)
(mushroom_rl.algorithms.value.td.SARSALambda class method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous class method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning class method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda class method)
(mushroom_rl.algorithms.value.td.WeightedQLearning class method)
(mushroom_rl.approximators.parametric.linear.LinearApproximator class method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator class method)
(mushroom_rl.approximators.regressor.Regressor class method)
(mushroom_rl.core.agent.Agent class method)
(mushroom_rl.core.environment.MDPInfo class method)
(mushroom_rl.core.serialization.Serializable class method)
(mushroom_rl.distributions.distribution.Distribution class method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution class method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution class method)
(mushroom_rl.distributions.gaussian.GaussianDistribution class method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy class method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy class method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy class method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy class method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy class method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy class method)
(mushroom_rl.policy.noise_policy.ClippedGaussianPolicy class method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy class method)
(mushroom_rl.policy.policy.ParametricPolicy class method)
(mushroom_rl.policy.policy.Policy class method)
(mushroom_rl.policy.td_policy.Boltzmann class method)
(mushroom_rl.policy.td_policy.EpsGreedy class method)
(mushroom_rl.policy.td_policy.Mellowmax class method)
(mushroom_rl.policy.td_policy.Mellowmax.MellowmaxParameter class method)
(mushroom_rl.policy.td_policy.TDPolicy class method)
(mushroom_rl.policy.torch_policy.BoltzmannTorchPolicy class method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy class method)
(mushroom_rl.policy.torch_policy.TorchPolicy class method)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace class method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace class method)
(mushroom_rl.utils.parameters.ExponentialParameter class method)
(mushroom_rl.utils.parameters.LinearParameter class method)
(mushroom_rl.utils.parameters.Parameter class method)
(mushroom_rl.utils.replay_memory.PrioritizedReplayMemory class method)
(mushroom_rl.utils.replay_memory.ReplayMemory class method)
(mushroom_rl.utils.table.EnsembleTable class method)
(mushroom_rl.utils.table.Table class method)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter class method)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter class method)
(mushroom_rl.utils.variance_parameters.VarianceParameter class method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter class method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter class method)
load_zip() (mushroom_rl.utils.eligibility_trace.AccumulatingTrace class method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace class method)
log_agent() (DataLogger method)
(Logger method)
log_best_agent() (DataLogger method)
(Logger method)
log_numpy() (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)
low (Box attribute)
LQR (class in mushroom_rl.environments.lqr)
LSPI (class in mushroom_rl.algorithms.value.batch_td)
M
make() (AbstractGridWorld static method)
(Atari 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)
(InvertedPendulum static method)
(LQR static method)
(MuJoCo static method)
(PuddleWorld static method)
(Segway static method)
(ShipSteering static method)
max_p (SumTree attribute)
max_priority (PrioritizedReplayMemory attribute)
MaxAndSkip (class in mushroom_rl.environments.atari)
MaxminDQN (class in mushroom_rl.algorithms.value.dqn)
MaxminQLearning (class in mushroom_rl.algorithms.value.td)
MDPInfo (class in mushroom_rl.core.environment)
Mellowmax (class in mushroom_rl.policy.td_policy)
Mellowmax.MellowmaxParameter (class in mushroom_rl.policy.td_policy)
metadata (MaxAndSkip attribute)
minibatch_generator() (in module mushroom_rl.utils.minibatches)
minibatch_number() (in module mushroom_rl.utils.minibatches)
mk_dir_recursive() (in module mushroom_rl.utils.folder)
mle() (Distribution method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
model (EnsembleTable attribute)
(Regressor attribute)
MuJoCo (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.linear (module)
mushroom_rl.approximators.parametric.torch_approximator (module)
mushroom_rl.approximators.regressor (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.atari (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.mujoco (module)
mushroom_rl.environments.puddle_world (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.gaussian_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.solvers.car_on_hill (module)
mushroom_rl.solvers.dynamic_programming (module)
mushroom_rl.solvers.lqr (module)
mushroom_rl.utils.angles (module)
mushroom_rl.utils.callbacks (module)
mushroom_rl.utils.dataset (module)
mushroom_rl.utils.eligibility_trace (module)
mushroom_rl.utils.features (module)
mushroom_rl.utils.folder (module)
mushroom_rl.utils.frames (module)
mushroom_rl.utils.minibatches (module)
mushroom_rl.utils.numerical_gradient (module)
mushroom_rl.utils.parameters (module)
mushroom_rl.utils.replay_memory (module)
mushroom_rl.utils.spaces (module)
mushroom_rl.utils.table (module)
mushroom_rl.utils.torch (module)
mushroom_rl.utils.value_functions (module)
mushroom_rl.utils.variance_parameters (module)
mushroom_rl.utils.viewer (module)
N
n_actions (AccumulatingTrace attribute)
(ReplacingTrace attribute)
(Table attribute)
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)
np_random (MaxAndSkip attribute)
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)
O
ObservationType (class in mushroom_rl.environments.mujoco)
OrnsteinUhlenbeckPolicy (class in mushroom_rl.policy.noise_policy)
output_shape (Regressor attribute)
P
Parameter (class in mushroom_rl.utils.parameters)
parameters() (BoltzmannTorchPolicy method)
(GaussianTorchPolicy method)
(TorchPolicy method)
parameters_size (Distribution attribute)
(GaussianCholeskyDistribution attribute)
(GaussianDiagonalDistribution attribute)
(GaussianDistribution attribute)
ParametricPolicy (class in mushroom_rl.policy.policy)
parse_dataset() (in module mushroom_rl.utils.dataset)
parse_grid() (in module mushroom_rl.environments.generators.grid_world)
(in module mushroom_rl.environments.generators.taxi)
path (DataLogger attribute)
(Logger attribute)
PGPE (class in mushroom_rl.algorithms.policy_search.black_box_optimization)
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)
PPO (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
predict() (AccumulatingTrace method)
(EnsembleTable method)
(LinearApproximator method)
(Regressor method)
(ReplacingTrace method)
(Table method)
(TorchApproximator method)
preprocess_frame() (in module mushroom_rl.utils.frames)
PrioritizedReplayMemory (class in mushroom_rl.utils.replay_memory)
PuddleWorld (class in mushroom_rl.environments.puddle_world)
Q
QLambda (class in mushroom_rl.algorithms.value.td)
QLearning (class in mushroom_rl.algorithms.value.td)
quat_to_euler() (in module mushroom_rl.utils.angles)
R
Rainbow (class in mushroom_rl.algorithms.value.dqn)
register() (mushroom_rl.core.environment.Environment class method)
(mushroom_rl.environments.atari.Atari class method)
(mushroom_rl.environments.car_on_hill.CarOnHill class method)
(mushroom_rl.environments.cart_pole.CartPole class method)
(mushroom_rl.environments.dm_control_env.DMControl class method)
(mushroom_rl.environments.finite_mdp.FiniteMDP class method)
(mushroom_rl.environments.grid_world.AbstractGridWorld class method)
(mushroom_rl.environments.grid_world.GridWorld class method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt class method)
(mushroom_rl.environments.gym_env.Gym class method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum class method)
(mushroom_rl.environments.lqr.LQR class method)
(mushroom_rl.environments.mujoco.MuJoCo class method)
(mushroom_rl.environments.puddle_world.PuddleWorld class method)
(mushroom_rl.environments.segway.Segway class method)
(mushroom_rl.environments.ship_steering.ShipSteering class method)
Regressor (class in mushroom_rl.approximators.regressor)
REINFORCE (class in mushroom_rl.algorithms.policy_search.policy_gradient)
render() (MaxAndSkip method)
ReplacingTrace (class in mushroom_rl.utils.eligibility_trace)
ReplayMemory (class in mushroom_rl.utils.replay_memory)
REPS (class in mushroom_rl.algorithms.policy_search.black_box_optimization)
reset() (AbstractGaussianPolicy method)
(AbstractGridWorld method)
(AccumulatingTrace method)
(Atari method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(CarOnHill method)
(CartPole method)
(ClippedGaussianPolicy method)
(Core method)
(DMControl method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(EnsembleTable method)
(Environment method)
(EpsGreedy method)
(FiniteMDP method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(InvertedPendulum method)
(LQR method)
(MaxAndSkip method)
(Mellowmax method)
(MuJoCo method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Policy method)
(PuddleWorld method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(Segway method)
(ShipSteering method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TDPolicy method)
(TorchPolicy method)
reward_range (MaxAndSkip attribute)
RLearning (class in mushroom_rl.algorithms.value.td)
RQLearning (class in mushroom_rl.algorithms.value.td)
RWR (class in mushroom_rl.algorithms.policy_search.black_box_optimization)
S
SAC (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
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() (A2C method)
(AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(EpsGreedy method)
(ExpectedSARSA method)
(ExponentialParameter method)
(FQI method)
(GPOMDP method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LSPI method)
(LinearApproximator method)
(LinearParameter method)
(MDPInfo method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Serializable method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(Table method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
(eNAC method)
save_zip() (A2C method)
(AbstractDQN method)
(AbstractGaussianPolicy method)
(AccumulatingTrace method)
(Agent method)
(AveragedDQN method)
(Boltzmann method)
(BoltzmannTorchPolicy method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ClippedGaussianPolicy method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(Distribution method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(EnsembleTable method)
(EpsGreedy method)
(ExpectedSARSA method)
(ExponentialParameter method)
(FQI method)
(GPOMDP method)
(GaussianCholeskyDistribution method)
(GaussianDiagonalDistribution method)
(GaussianDistribution method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LSPI method)
(LinearApproximator method)
(LinearParameter method)
(MDPInfo method)
(MaxminDQN method)
(MaxminQLearning method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(NoisyDQN method)
(OrnsteinUhlenbeckPolicy method)
(PGPE method)
(PPO method)
(Parameter method)
(ParametricPolicy method)
(Policy method)
(PrioritizedReplayMemory method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(ReplacingTrace method)
(ReplayMemory method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Serializable method)
(SpeedyQLearning method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TDPolicy method)
(TRPO method)
(Table method)
(TorchApproximator method)
(TorchPolicy method)
(TrueOnlineSARSALambda method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WeightedQLearning method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
(eNAC method)
screen (Viewer attribute)
seed() (AbstractGridWorld method)
(Atari method)
(CarOnHill method)
(CartPole method)
(DMControl method)
(Environment method)
(FiniteMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(InvertedPendulum method)
(LQR method)
(MaxAndSkip method)
(MuJoCo method)
(PuddleWorld method)
(Segway method)
(ShipSteering method)
Segway (class in mushroom_rl.environments.segway)
select_first_episodes() (in module mushroom_rl.utils.dataset)
select_random_samples() (in module mushroom_rl.utils.dataset)
Serializable (class in mushroom_rl.core.serialization)
set_beta() (Boltzmann method)
(Mellowmax method)
set_episode_end() (Atari method)
set_epsilon() (EpsGreedy method)
set_logger() (A2C method)
(AbstractDQN method)
(Agent method)
(AveragedDQN method)
(BoostedFQI method)
(COPDAC_Q method)
(CategoricalDQN method)
(ConstrainedREPS method)
(DDPG method)
(DQN method)
(DeepAC method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(ExpectedSARSA method)
(FQI method)
(GPOMDP method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(NoisyDQN method)
(PGPE method)
(PPO method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(Regressor method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TRPO method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
(eNAC 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)
(DeterministicPolicy method)
(DiagonalGaussianPolicy method)
(GaussianPolicy method)
(GaussianTorchPolicy method)
(LinearApproximator method)
(OrnsteinUhlenbeckPolicy method)
(ParametricPolicy method)
(Regressor method)
(StateLogStdGaussianPolicy method)
(StateStdGaussianPolicy method)
(TorchApproximator method)
(TorchPolicy method)
(in module mushroom_rl.utils.torch)
shape (AccumulatingTrace attribute)
(Box attribute)
(Discrete attribute)
(ExponentialParameter attribute)
(LinearParameter attribute)
(MDPInfo attribute)
(Mellowmax.MellowmaxParameter attribute)
(Parameter attribute)
(ReplacingTrace attribute)
(Table attribute)
(VarianceDecreasingParameter attribute)
(VarianceIncreasingParameter attribute)
(VarianceParameter attribute)
(WindowedVarianceIncreasingParameter attribute)
(WindowedVarianceParameter attribute)
ShipSteering (class in mushroom_rl.environments.ship_steering)
shortest_angular_distance() (in module mushroom_rl.utils.angles)
size (Discrete attribute)
(MDPInfo attribute)
(ReplayMemory attribute)
(SumTree attribute)
(Viewer attribute)
solve_car_on_hill() (in module mushroom_rl.solvers.car_on_hill)
SpeedyQLearning (class in mushroom_rl.algorithms.value.td)
square() (Viewer method)
StateLogStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
StateStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
step() (AbstractGridWorld method)
(Atari method)
(CarOnHill method)
(CartPole method)
(DMControl method)
(Environment method)
(FiniteMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(InvertedPendulum method)
(LQR method)
(MaxAndSkip method)
(MuJoCo method)
(PuddleWorld method)
(Segway method)
(ShipSteering method)
(in module mushroom_rl.solvers.car_on_hill)
StochasticAC (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
StochasticAC_AVG (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
stop() (A2C method)
(AbstractDQN method)
(AbstractGridWorld method)
(Agent method)
(Atari method)
(AveragedDQN method)
(BoostedFQI method)
(COPDAC_Q method)
(CarOnHill method)
(CartPole method)
(CategoricalDQN method)
(ConstrainedREPS method)
(DDPG method)
(DMControl method)
(DQN method)
(DeepAC method)
(DoubleDQN method)
(DoubleFQI method)
(DoubleQLearning method)
(DuelingDQN method)
(Environment method)
(ExpectedSARSA method)
(FQI method)
(FiniteMDP method)
(GPOMDP method)
(GridWorld method)
(GridWorldVanHasselt method)
(Gym method)
(InvertedPendulum method)
(LQR method)
(LSPI method)
(MaxminDQN method)
(MaxminQLearning method)
(MuJoCo method)
(NoisyDQN method)
(PGPE method)
(PPO method)
(PuddleWorld method)
(QLambda method)
(QLearning method)
(REINFORCE method)
(REPS method)
(RLearning method)
(RQLearning method)
(RWR method)
(Rainbow method)
(SAC method)
(SARSA method)
(SARSALambda method)
(SARSALambdaContinuous method)
(Segway method)
(ShipSteering method)
(SpeedyQLearning method)
(StochasticAC method)
(StochasticAC_AVG method)
(TD3 method)
(TRPO method)
(TrueOnlineSARSALambda method)
(WeightedQLearning method)
(eNAC method)
strong_line() (ConsoleLogger method)
(Logger method)
SumTree (class in mushroom_rl.utils.replay_memory)
T
Table (class in mushroom_rl.utils.table)
TD3 (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
TDPolicy (class in mushroom_rl.policy.td_policy)
Tiles (class in mushroom_rl.features.tiles.tiles)
to_float_tensor() (in module mushroom_rl.utils.torch)
to_int_tensor() (in module mushroom_rl.utils.torch)
TorchApproximator (class in mushroom_rl.approximators.parametric.torch_approximator)
TorchPolicy (class in mushroom_rl.policy.torch_policy)
torque_arrow() (Viewer method)
total_p (SumTree attribute)
TRPO (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
TrueOnlineSARSALambda (class in mushroom_rl.algorithms.value.td)
U
uniform_grid() (in module mushroom_rl.utils.features)
unwrapped (MaxAndSkip attribute)
update() (AccumulatingTrace method)
(Boltzmann method)
(EpsGreedy method)
(ExponentialParameter method)
(LinearParameter method)
(Mellowmax method)
(Mellowmax.MellowmaxParameter method)
(Parameter method)
(PrioritizedReplayMemory method)
(ReplacingTrace method)
(SumTree method)
(VarianceDecreasingParameter method)
(VarianceIncreasingParameter method)
(VarianceParameter method)
(WindowedVarianceIncreasingParameter method)
(WindowedVarianceParameter method)
use_cuda (BoltzmannTorchPolicy attribute)
(GaussianTorchPolicy attribute)
(TorchPolicy attribute)
V
value_iteration() (in module mushroom_rl.solvers.dynamic_programming)
VarianceDecreasingParameter (class in mushroom_rl.utils.variance_parameters)
VarianceIncreasingParameter (class in mushroom_rl.utils.variance_parameters)
VarianceParameter (class in mushroom_rl.utils.variance_parameters)
Viewer (class in mushroom_rl.utils.viewer)
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 attribute)
(ClippedGaussianPolicy attribute)
(DeterministicPolicy attribute)
(DiagonalGaussianPolicy attribute)
(GaussianPolicy attribute)
(LinearApproximator attribute)
(OrnsteinUhlenbeckPolicy attribute)
(ParametricPolicy attribute)
(Regressor attribute)
(StateLogStdGaussianPolicy attribute)
(StateStdGaussianPolicy attribute)
(TorchApproximator attribute)
WindowedVarianceIncreasingParameter (class in mushroom_rl.utils.variance_parameters)
WindowedVarianceParameter (class in mushroom_rl.utils.variance_parameters)
Z
zero_grad() (in module mushroom_rl.utils.torch)
Read the Docs
v: 1.7.0
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
Free document hosting provided by
Read the Docs
.