MushroomRL
1.4.0
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
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__() (mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
(mushroom_rl.features.basis.fourier.FourierBasis method)
(mushroom_rl.features.basis.gaussian_rbf.GaussianRBF method)
(mushroom_rl.features.basis.polynomial.PolynomialBasis method)
(mushroom_rl.features.tiles.tiles.Tiles method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
(mushroom_rl.policy.policy.Policy method)
(mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.policy.td_policy.TDPolicy method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
(mushroom_rl.utils.callbacks.Callback method)
(mushroom_rl.utils.callbacks.CollectDataset method)
(mushroom_rl.utils.callbacks.CollectMaxQ method)
(mushroom_rl.utils.callbacks.CollectParameters method)
(mushroom_rl.utils.callbacks.CollectQ method)
(mushroom_rl.utils.parameters.AdaptiveParameter method)
(mushroom_rl.utils.parameters.ExponentialParameter method)
(mushroom_rl.utils.parameters.LinearParameter method)
(mushroom_rl.utils.parameters.Parameter method)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter method)
__init__ (mushroom_rl.distributions.distribution.Distribution attribute)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy attribute)
(mushroom_rl.policy.policy.ParametricPolicy attribute)
(mushroom_rl.policy.policy.Policy attribute)
__init__() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
(mushroom_rl.approximators.parametric.linear.LinearApproximator method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator method)
(mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.core.core.Core method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
(mushroom_rl.environments.atari.Atari method)
(mushroom_rl.environments.atari.LazyFrames method)
(mushroom_rl.environments.atari.MaxAndSkip method)
(mushroom_rl.environments.car_on_hill.CarOnHill method)
(mushroom_rl.environments.cart_pole.CartPole method)
(mushroom_rl.environments.dm_control_env.DMControl method)
(mushroom_rl.environments.environment.Environment method)
(mushroom_rl.environments.environment.MDPInfo method)
(mushroom_rl.environments.finite_mdp.FiniteMDP method)
(mushroom_rl.environments.grid_world.AbstractGridWorld method)
(mushroom_rl.environments.grid_world.GridWorld method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt method)
(mushroom_rl.environments.gym_env.Gym method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum method)
(mushroom_rl.environments.lqr.LQR method)
(mushroom_rl.environments.mujoco.MuJoCo method)
(mushroom_rl.environments.puddle_world.PuddleWorld method)
(mushroom_rl.environments.segway.Segway method)
(mushroom_rl.environments.ship_steering.ShipSteering method)
(mushroom_rl.features.basis.fourier.FourierBasis method)
(mushroom_rl.features.basis.gaussian_rbf.GaussianRBF method)
(mushroom_rl.features.basis.polynomial.PolynomialBasis method)
(mushroom_rl.features.tensors.gaussian_tensor.PyTorchGaussianRBF method)
(mushroom_rl.features.tiles.tiles.Tiles method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.policy.td_policy.TDPolicy method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
(mushroom_rl.utils.callbacks.Callback method)
(mushroom_rl.utils.callbacks.CollectMaxQ method)
(mushroom_rl.utils.callbacks.CollectParameters method)
(mushroom_rl.utils.callbacks.CollectQ method)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace method)
(mushroom_rl.utils.parameters.AdaptiveParameter method)
(mushroom_rl.utils.parameters.ExponentialParameter method)
(mushroom_rl.utils.parameters.LinearParameter method)
(mushroom_rl.utils.parameters.Parameter method)
(mushroom_rl.utils.replay_memory.PrioritizedReplayMemory method)
(mushroom_rl.utils.replay_memory.ReplayMemory method)
(mushroom_rl.utils.replay_memory.SumTree method)
(mushroom_rl.utils.spaces.Box method)
(mushroom_rl.utils.spaces.Discrete method)
(mushroom_rl.utils.table.EnsembleTable method)
(mushroom_rl.utils.table.Table method)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter method)
(mushroom_rl.utils.viewer.ImageViewer method)
(mushroom_rl.utils.viewer.Viewer method)
_add_save_attr() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
_bound() (mushroom_rl.environments.atari.Atari static method)
(mushroom_rl.environments.car_on_hill.CarOnHill static method)
(mushroom_rl.environments.cart_pole.CartPole static method)
(mushroom_rl.environments.dm_control_env.DMControl static method)
(mushroom_rl.environments.environment.Environment static method)
(mushroom_rl.environments.finite_mdp.FiniteMDP static method)
(mushroom_rl.environments.grid_world.AbstractGridWorld static method)
(mushroom_rl.environments.grid_world.GridWorld static method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt static method)
(mushroom_rl.environments.gym_env.Gym static method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum static method)
(mushroom_rl.environments.lqr.LQR static method)
(mushroom_rl.environments.mujoco.MuJoCo static method)
(mushroom_rl.environments.puddle_world.PuddleWorld static method)
(mushroom_rl.environments.segway.Segway static method)
(mushroom_rl.environments.ship_steering.ShipSteering static method)
_compute() (mushroom_rl.utils.parameters.ExponentialParameter method)
(mushroom_rl.utils.parameters.LinearParameter method)
(mushroom_rl.utils.parameters.Parameter method)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter method)
_compute_action() (mushroom_rl.environments.mujoco.MuJoCo method)
_compute_exponents() (mushroom_rl.features.basis.polynomial.PolynomialBasis static method)
_compute_gradient() (mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
_episode_end_update() (mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
_fit() (mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
_fit_boosted() (mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
_init_update() (mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
_next_q() (mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
_optimize_actor_parameters() (mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
_parse() (mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.value.td.DoubleQLearning static method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA static method)
(mushroom_rl.algorithms.value.td.QLearning static method)
(mushroom_rl.algorithms.value.td.RLearning static method)
(mushroom_rl.algorithms.value.td.RQLearning static method)
(mushroom_rl.algorithms.value.td.SARSA static method)
(mushroom_rl.algorithms.value.td.SARSALambda static method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous static method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning static method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda static method)
(mushroom_rl.algorithms.value.td.WeightedQLearning static method)
_post_load() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
_preprocess() (mushroom_rl.core.core.Core method)
_preprocess_action() (mushroom_rl.environments.mujoco.MuJoCo method)
_simulation_post_step() (mushroom_rl.environments.mujoco.MuJoCo method)
_simulation_pre_step() (mushroom_rl.environments.mujoco.MuJoCo method)
_step() (mushroom_rl.core.core.Core method)
_step_finalize() (mushroom_rl.environments.mujoco.MuJoCo method)
_step_init() (mushroom_rl.environments.mujoco.MuJoCo method)
_step_update() (mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
_update() (mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
_update_parameters() (mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
_update_target() (mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
A
A2C (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
AbstractGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
AbstractGridWorld (class in mushroom_rl.environments.grid_world)
AccumulatingTrace (class in mushroom_rl.utils.eligibility_trace)
AdaptiveParameter (class in mushroom_rl.utils.parameters)
add() (mushroom_rl.utils.replay_memory.PrioritizedReplayMemory method)
(mushroom_rl.utils.replay_memory.ReplayMemory method)
(mushroom_rl.utils.replay_memory.SumTree method)
Agent (class in mushroom_rl.algorithms.agent)
arrays_as_dataset() (in module mushroom_rl.utils.dataset)
arrow_head() (mushroom_rl.utils.viewer.Viewer method)
Atari (class in mushroom_rl.environments.atari)
AveragedDQN (class in mushroom_rl.algorithms.value.dqn)
B
background_image() (mushroom_rl.utils.viewer.Viewer method)
bfs() (in module mushroom_rl.solvers.car_on_hill)
Boltzmann (class in mushroom_rl.policy.td_policy)
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)
check_collision() (mushroom_rl.environments.mujoco.MuJoCo method)
circle() (mushroom_rl.utils.viewer.Viewer method)
clean() (mushroom_rl.utils.callbacks.Callback method)
close() (mushroom_rl.environments.atari.MaxAndSkip method)
(mushroom_rl.utils.viewer.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_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)
COPDAC_Q (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic)
copy() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
Core (class in mushroom_rl.core.core)
D
DDPG (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
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() (mushroom_rl.approximators.parametric.linear.LinearApproximator method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator method)
(mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
diff_log() (mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
Discrete (class in mushroom_rl.utils.spaces)
display() (mushroom_rl.utils.viewer.ImageViewer method)
(mushroom_rl.utils.viewer.Viewer method)
Distribution (class in mushroom_rl.distributions.distribution)
distribution() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
distribution_t() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.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() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
(mushroom_rl.policy.policy.Policy method)
(mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.policy.td_policy.TDPolicy method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
draw_action_t() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
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() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
entropy_t() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
Environment (class in mushroom_rl.environments.environment)
episode_start() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
episodes_length() (in module mushroom_rl.utils.dataset)
EpsGreedy (class in mushroom_rl.policy.td_policy)
euler_to_quat() (in module mushroom_rl.utils.angles)
evaluate() (mushroom_rl.core.core.Core 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() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
(mushroom_rl.approximators.parametric.linear.LinearApproximator method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator method)
(mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace method)
(mushroom_rl.utils.table.EnsembleTable method)
(mushroom_rl.utils.table.Table method)
force_arrow() (mushroom_rl.utils.viewer.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() (mushroom_rl.utils.viewer.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)
GaussianTorchPolicy (class in mushroom_rl.policy.torch_policy)
generate() (mushroom_rl.environments.lqr.LQR static method)
(mushroom_rl.features.basis.fourier.FourierBasis static method)
(mushroom_rl.features.basis.gaussian_rbf.GaussianRBF static method)
(mushroom_rl.features.basis.polynomial.PolynomialBasis static method)
(mushroom_rl.features.tensors.gaussian_tensor.PyTorchGaussianRBF static method)
(mushroom_rl.features.tiles.tiles.Tiles 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() (mushroom_rl.utils.callbacks.Callback method)
(mushroom_rl.utils.replay_memory.PrioritizedReplayMemory method)
(mushroom_rl.utils.replay_memory.ReplayMemory method)
(mushroom_rl.utils.replay_memory.SumTree method)
get_action_features() (in module mushroom_rl.features.features)
get_collision_force() (mushroom_rl.environments.mujoco.MuJoCo method)
get_gradient() (in module mushroom_rl.utils.torch)
get_parameters() (mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
get_q() (mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.policy.td_policy.TDPolicy method)
get_regressor() (mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
get_value() (mushroom_rl.utils.parameters.ExponentialParameter method)
(mushroom_rl.utils.parameters.LinearParameter method)
(mushroom_rl.utils.parameters.Parameter method)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter method)
get_weights() (in module mushroom_rl.utils.torch)
(mushroom_rl.approximators.parametric.linear.LinearApproximator method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator method)
(mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.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
high (mushroom_rl.utils.spaces.Box attribute)
I
ImageViewer (class in mushroom_rl.utils.viewer)
info (mushroom_rl.environments.atari.Atari attribute)
(mushroom_rl.environments.car_on_hill.CarOnHill attribute)
(mushroom_rl.environments.cart_pole.CartPole attribute)
(mushroom_rl.environments.dm_control_env.DMControl attribute)
(mushroom_rl.environments.environment.Environment attribute)
(mushroom_rl.environments.finite_mdp.FiniteMDP attribute)
(mushroom_rl.environments.grid_world.AbstractGridWorld attribute)
(mushroom_rl.environments.grid_world.GridWorld attribute)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt attribute)
(mushroom_rl.environments.gym_env.Gym attribute)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum attribute)
(mushroom_rl.environments.lqr.LQR attribute)
(mushroom_rl.environments.mujoco.MuJoCo attribute)
(mushroom_rl.environments.puddle_world.PuddleWorld attribute)
(mushroom_rl.environments.segway.Segway attribute)
(mushroom_rl.environments.ship_steering.ShipSteering attribute)
initialized (mushroom_rl.utils.replay_memory.PrioritizedReplayMemory attribute)
(mushroom_rl.utils.replay_memory.ReplayMemory attribute)
input_shape (mushroom_rl.approximators.regressor.Regressor attribute)
InvertedPendulum (class in mushroom_rl.environments.inverted_pendulum)
is_absorbing() (mushroom_rl.environments.mujoco.MuJoCo method)
L
LazyFrames (class in mushroom_rl.environments.atari)
learn() (mushroom_rl.core.core.Core method)
line() (mushroom_rl.utils.viewer.Viewer method)
LinearApproximator (class in mushroom_rl.approximators.parametric.linear)
LinearParameter (class in mushroom_rl.utils.parameters)
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.agent.Agent 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.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.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.td.DoubleQLearning class method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA 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)
log_pdf() (mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
log_prob_t() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
low (mushroom_rl.utils.spaces.Box attribute)
LQR (class in mushroom_rl.environments.lqr)
LSPI (class in mushroom_rl.algorithms.value.batch_td)
M
max_p (mushroom_rl.utils.replay_memory.SumTree attribute)
max_priority (mushroom_rl.utils.replay_memory.PrioritizedReplayMemory attribute)
MaxAndSkip (class in mushroom_rl.environments.atari)
MDPInfo (class in mushroom_rl.environments.environment)
Mellowmax (class in mushroom_rl.policy.td_policy)
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() (mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
model (mushroom_rl.approximators.regressor.Regressor attribute)
(mushroom_rl.utils.table.EnsembleTable 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.agent (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.core (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.environment (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.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.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.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 (mushroom_rl.utils.eligibility_trace.AccumulatingTrace attribute)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace attribute)
(mushroom_rl.utils.table.Table attribute)
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_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 (mushroom_rl.approximators.regressor.Regressor attribute)
P
Parameter (class in mushroom_rl.utils.parameters)
parameters() (mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
parameters_size (mushroom_rl.distributions.distribution.Distribution attribute)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution attribute)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution attribute)
(mushroom_rl.distributions.gaussian.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)
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() (mushroom_rl.utils.viewer.Viewer method)
PolynomialBasis (class in mushroom_rl.features.basis.polynomial)
PPO (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic)
predict() (mushroom_rl.approximators.parametric.linear.LinearApproximator method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator method)
(mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace method)
(mushroom_rl.utils.table.EnsembleTable method)
(mushroom_rl.utils.table.Table method)
PrioritizedReplayMemory (class in mushroom_rl.utils.replay_memory)
PuddleWorld (class in mushroom_rl.environments.puddle_world)
PyTorchGaussianRBF (class in mushroom_rl.features.tensors.gaussian_tensor)
Q
QLearning (class in mushroom_rl.algorithms.value.td)
quat_to_euler() (in module mushroom_rl.utils.angles)
R
read_data() (mushroom_rl.environments.mujoco.MuJoCo method)
Regressor (class in mushroom_rl.approximators.regressor)
REINFORCE (class in mushroom_rl.algorithms.policy_search.policy_gradient)
render() (mushroom_rl.environments.atari.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() (mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.core.core.Core method)
(mushroom_rl.environments.atari.Atari method)
(mushroom_rl.environments.atari.MaxAndSkip method)
(mushroom_rl.environments.car_on_hill.CarOnHill method)
(mushroom_rl.environments.cart_pole.CartPole method)
(mushroom_rl.environments.dm_control_env.DMControl method)
(mushroom_rl.environments.environment.Environment method)
(mushroom_rl.environments.finite_mdp.FiniteMDP method)
(mushroom_rl.environments.grid_world.AbstractGridWorld method)
(mushroom_rl.environments.grid_world.GridWorld method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt method)
(mushroom_rl.environments.gym_env.Gym method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum method)
(mushroom_rl.environments.lqr.LQR method)
(mushroom_rl.environments.mujoco.MuJoCo method)
(mushroom_rl.environments.puddle_world.PuddleWorld method)
(mushroom_rl.environments.segway.Segway method)
(mushroom_rl.environments.ship_steering.ShipSteering method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
(mushroom_rl.policy.policy.Policy method)
(mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.policy.td_policy.TDPolicy method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace method)
(mushroom_rl.utils.replay_memory.ReplayMemory method)
(mushroom_rl.utils.table.EnsembleTable method)
reward() (mushroom_rl.environments.mujoco.MuJoCo method)
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() (mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.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() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
screen (mushroom_rl.utils.viewer.Viewer attribute)
seed() (mushroom_rl.environments.atari.Atari method)
(mushroom_rl.environments.atari.MaxAndSkip method)
(mushroom_rl.environments.car_on_hill.CarOnHill method)
(mushroom_rl.environments.cart_pole.CartPole method)
(mushroom_rl.environments.dm_control_env.DMControl method)
(mushroom_rl.environments.environment.Environment method)
(mushroom_rl.environments.finite_mdp.FiniteMDP method)
(mushroom_rl.environments.grid_world.AbstractGridWorld method)
(mushroom_rl.environments.grid_world.GridWorld method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt method)
(mushroom_rl.environments.gym_env.Gym method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum method)
(mushroom_rl.environments.lqr.LQR method)
(mushroom_rl.environments.mujoco.MuJoCo method)
(mushroom_rl.environments.puddle_world.PuddleWorld method)
(mushroom_rl.environments.segway.Segway method)
(mushroom_rl.environments.ship_steering.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)
set_beta() (mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.Mellowmax method)
set_episode_end() (mushroom_rl.environments.atari.Atari method)
set_epsilon() (mushroom_rl.policy.td_policy.EpsGreedy method)
set_parameters() (mushroom_rl.distributions.distribution.Distribution method)
(mushroom_rl.distributions.gaussian.GaussianCholeskyDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDiagonalDistribution method)
(mushroom_rl.distributions.gaussian.GaussianDistribution method)
set_q() (mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.policy.td_policy.TDPolicy method)
set_sigma() (mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
set_std() (mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
set_weights() (in module mushroom_rl.utils.torch)
(mushroom_rl.approximators.parametric.linear.LinearApproximator method)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator method)
(mushroom_rl.approximators.regressor.Regressor method)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy method)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy method)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy method)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy method)
(mushroom_rl.policy.policy.ParametricPolicy method)
(mushroom_rl.policy.torch_policy.GaussianTorchPolicy method)
(mushroom_rl.policy.torch_policy.TorchPolicy method)
setup() (mushroom_rl.environments.mujoco.MuJoCo method)
shape (mushroom_rl.environments.environment.MDPInfo attribute)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace attribute)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace attribute)
(mushroom_rl.utils.parameters.ExponentialParameter attribute)
(mushroom_rl.utils.parameters.LinearParameter attribute)
(mushroom_rl.utils.parameters.Parameter attribute)
(mushroom_rl.utils.spaces.Box attribute)
(mushroom_rl.utils.spaces.Discrete attribute)
(mushroom_rl.utils.table.Table attribute)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter attribute)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter attribute)
(mushroom_rl.utils.variance_parameters.VarianceParameter attribute)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter attribute)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter attribute)
ShipSteering (class in mushroom_rl.environments.ship_steering)
shortest_angular_distance() (in module mushroom_rl.utils.angles)
size (mushroom_rl.environments.environment.MDPInfo attribute)
(mushroom_rl.utils.replay_memory.ReplayMemory attribute)
(mushroom_rl.utils.replay_memory.SumTree attribute)
(mushroom_rl.utils.spaces.Discrete attribute)
(mushroom_rl.utils.viewer.Viewer attribute)
solve_car_on_hill() (in module mushroom_rl.solvers.car_on_hill)
SpeedyQLearning (class in mushroom_rl.algorithms.value.td)
square() (mushroom_rl.utils.viewer.Viewer method)
StateLogStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
StateStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy)
step() (in module mushroom_rl.solvers.car_on_hill)
(mushroom_rl.environments.atari.Atari method)
(mushroom_rl.environments.atari.MaxAndSkip method)
(mushroom_rl.environments.car_on_hill.CarOnHill method)
(mushroom_rl.environments.cart_pole.CartPole method)
(mushroom_rl.environments.dm_control_env.DMControl method)
(mushroom_rl.environments.environment.Environment method)
(mushroom_rl.environments.finite_mdp.FiniteMDP method)
(mushroom_rl.environments.grid_world.AbstractGridWorld method)
(mushroom_rl.environments.grid_world.GridWorld method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt method)
(mushroom_rl.environments.gym_env.Gym method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum method)
(mushroom_rl.environments.lqr.LQR method)
(mushroom_rl.environments.mujoco.MuJoCo method)
(mushroom_rl.environments.puddle_world.PuddleWorld method)
(mushroom_rl.environments.segway.Segway method)
(mushroom_rl.environments.ship_steering.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() (mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC method)
(mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3 method)
(mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO method)
(mushroom_rl.algorithms.agent.Agent method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.PGPE method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.REPS method)
(mushroom_rl.algorithms.policy_search.black_box_optimization.RWR method)
(mushroom_rl.algorithms.policy_search.policy_gradient.GPOMDP method)
(mushroom_rl.algorithms.policy_search.policy_gradient.REINFORCE method)
(mushroom_rl.algorithms.policy_search.policy_gradient.eNAC method)
(mushroom_rl.algorithms.value.batch_td.DoubleFQI method)
(mushroom_rl.algorithms.value.batch_td.FQI method)
(mushroom_rl.algorithms.value.batch_td.LSPI method)
(mushroom_rl.algorithms.value.dqn.AveragedDQN method)
(mushroom_rl.algorithms.value.dqn.CategoricalDQN method)
(mushroom_rl.algorithms.value.dqn.DQN method)
(mushroom_rl.algorithms.value.dqn.DoubleDQN method)
(mushroom_rl.algorithms.value.td.DoubleQLearning method)
(mushroom_rl.algorithms.value.td.ExpectedSARSA method)
(mushroom_rl.algorithms.value.td.QLearning method)
(mushroom_rl.algorithms.value.td.RLearning method)
(mushroom_rl.algorithms.value.td.RQLearning method)
(mushroom_rl.algorithms.value.td.SARSA method)
(mushroom_rl.algorithms.value.td.SARSALambda method)
(mushroom_rl.algorithms.value.td.SARSALambdaContinuous method)
(mushroom_rl.algorithms.value.td.SpeedyQLearning method)
(mushroom_rl.algorithms.value.td.TrueOnlineSARSALambda method)
(mushroom_rl.algorithms.value.td.WeightedQLearning method)
(mushroom_rl.environments.atari.Atari method)
(mushroom_rl.environments.car_on_hill.CarOnHill method)
(mushroom_rl.environments.cart_pole.CartPole method)
(mushroom_rl.environments.dm_control_env.DMControl method)
(mushroom_rl.environments.environment.Environment method)
(mushroom_rl.environments.finite_mdp.FiniteMDP method)
(mushroom_rl.environments.grid_world.AbstractGridWorld method)
(mushroom_rl.environments.grid_world.GridWorld method)
(mushroom_rl.environments.grid_world.GridWorldVanHasselt method)
(mushroom_rl.environments.gym_env.Gym method)
(mushroom_rl.environments.inverted_pendulum.InvertedPendulum method)
(mushroom_rl.environments.lqr.LQR method)
(mushroom_rl.environments.mujoco.MuJoCo method)
(mushroom_rl.environments.puddle_world.PuddleWorld method)
(mushroom_rl.environments.segway.Segway method)
(mushroom_rl.environments.ship_steering.ShipSteering 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)
TorchApproximator (class in mushroom_rl.approximators.parametric.torch_approximator)
TorchPolicy (class in mushroom_rl.policy.torch_policy)
torque_arrow() (mushroom_rl.utils.viewer.Viewer method)
total_p (mushroom_rl.utils.replay_memory.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 (mushroom_rl.environments.atari.MaxAndSkip attribute)
update() (mushroom_rl.policy.td_policy.Boltzmann method)
(mushroom_rl.policy.td_policy.EpsGreedy method)
(mushroom_rl.policy.td_policy.Mellowmax method)
(mushroom_rl.utils.eligibility_trace.AccumulatingTrace method)
(mushroom_rl.utils.eligibility_trace.ReplacingTrace method)
(mushroom_rl.utils.parameters.ExponentialParameter method)
(mushroom_rl.utils.parameters.LinearParameter method)
(mushroom_rl.utils.parameters.Parameter method)
(mushroom_rl.utils.replay_memory.PrioritizedReplayMemory method)
(mushroom_rl.utils.replay_memory.SumTree method)
(mushroom_rl.utils.variance_parameters.VarianceDecreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.VarianceParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceIncreasingParameter method)
(mushroom_rl.utils.variance_parameters.WindowedVarianceParameter method)
use_cuda (mushroom_rl.policy.torch_policy.GaussianTorchPolicy attribute)
(mushroom_rl.policy.torch_policy.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)
W
WeightedQLearning (class in mushroom_rl.algorithms.value.td)
weights_size (mushroom_rl.approximators.parametric.linear.LinearApproximator attribute)
(mushroom_rl.approximators.parametric.torch_approximator.TorchApproximator attribute)
(mushroom_rl.approximators.regressor.Regressor attribute)
(mushroom_rl.policy.deterministic_policy.DeterministicPolicy attribute)
(mushroom_rl.policy.gaussian_policy.AbstractGaussianPolicy attribute)
(mushroom_rl.policy.gaussian_policy.DiagonalGaussianPolicy attribute)
(mushroom_rl.policy.gaussian_policy.GaussianPolicy attribute)
(mushroom_rl.policy.gaussian_policy.StateLogStdGaussianPolicy attribute)
(mushroom_rl.policy.gaussian_policy.StateStdGaussianPolicy attribute)
(mushroom_rl.policy.noise_policy.OrnsteinUhlenbeckPolicy attribute)
(mushroom_rl.policy.policy.ParametricPolicy attribute)
WindowedVarianceIncreasingParameter (class in mushroom_rl.utils.variance_parameters)
WindowedVarianceParameter (class in mushroom_rl.utils.variance_parameters)
write_data() (mushroom_rl.environments.mujoco.MuJoCo method)
Z
zero_grad() (in module mushroom_rl.utils.torch)
Read the Docs
v: 1.4.0
Versions
latest
1.4.0
1.2.0
1.1
dev
Downloads
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.