Index

_

__call__() (AbstractGaussianPolicy method) (AdamOptimizer method) (AdaptiveOptimizer method) (Approximator method) (Boltzmann method) (ClippedGaussianPolicy method) (ContextBuilder method) (DeterministicPolicy method) (Distribution method) (DMP method) (EpsGreedy method) (FourierBasis method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) (GaussianRBF method) (HistoryManager method) (Mellowmax.MellowmaxParameter method) (MinMaxPreprocessor method) (Optimizer method) (OrnsteinUhlenbeckPolicy method) (Parameter method) (Policy method) (PolynomialBasis method) (Preprocessor method) (ProMP method) (SGDOptimizer method) (StandardizationPreprocessor method) (Tiles method) (TorchPolicy method) (VideoRecorder method) (VoronoiTiles method) __init__() (A1Walking method) (A2C method) (AbstractDQN method) (AbstractGridWorld method) (ActorNetwork method) (AdamOptimizer method) (AdaptiveOptimizer method) (Agent method) (AgentInfo method) (AirHockeyBase method) (AirHockeyBaseBullet method) (AirHockeyDefend method) (AirHockeyDefendBullet method) (AirHockeyDouble method) (AirHockeyHit method) (AirHockeyHitBullet method) (AirHockeyPrepare method) (AirHockeyPrepareBullet method) (AirHockeyRepel method) (AirHockeyRepelBullet method) (AirHockeySingle method) (AirHockeySingleBullet method) (Ant method) (Approximator method) (Atari method) (AtariFeatureNetwork method) (AtariNetwork method) (AveragedDQN method) (BallInACup method) (BlackBoxOptimization method) (Boltzmann method) (BoltzmannTorchPolicy method) (BoostedFQI method) (Box method) (CarOnHill method) (CartPole method), [1] (CategoricalDQN method) (CategoricalNetwork method) (CategoricalWrapper method) (ClippedGaussianPolicy method) (CMAC method) (ConsoleLogger method) (ConstrainedREPS method) (ContextBuilder method) (COPDAC_Q method) (Core method) (CriticNetwork method) (CV2Viewer method) (DataLogger method) (Dataset method) (DatasetInfo method) (DDPG method) (DecayParameter method) (DeepAC method) (DeterministicPolicy method) (DiagonalGaussianPolicy method) (Discrete method) (Distribution method) (DMControl method) (DMP method) (DoubleFQI method) (DoubleQLearning method) (DuelingDQN method) (DuelingNetwork method) (eNAC method) (Ensemble method) (Environment method) (ePPO method) (EpsGreedy method) (ExpectedSARSA method) (FiniteMDP method) (FourierBasis method) (FQI method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) (GaussianPolicy method) (GaussianRBF method) (GaussianTorchPolicy method) (GenericBasisTensor method) (GPOMDP method) (GridWorld method) (GridWorldVanHasselt method) (Gymnasium method) (HalfCheetah method) (HistoryManager method) (HoneyBadgerWalking method) (Hopper method) (ImageViewer method) (InvertedPendulum method) (IsaacSim method) (LinearApproximator method) (LinearNetwork method) (LinearParameter method) (Logger method) (LQR method) (LSPI method) (MaxminDQN method) (MaxminQLearning method) (MDPInfo method) (Mellowmax method) (Mellowmax.MellowmaxParameter method) (MiniGrid method) (MiniGridBase method) (MiniGridRGB method) (MinMaxPreprocessor method) (MORE method) (MuJoCo method) (MultiMuJoCo method) (NoisyDQN method) (NoisyNetwork method) (NoisyNetwork.NoisyLinear method) (OmniIsaacGymEnv method) (Optimizer method) (OrnsteinUhlenbeckPolicy method) (Panda method) (Parameter method) (PegInsertion method) (PGPE method) (Pick method) (PolynomialBasis method) (PPO method) (PPO_BPTT method) (PrioritizedReplayMemory method) (ProMP method) (PuddleWorld method) (Push method) (PyBullet method) (QApproximatorAction method) (QApproximatorEnsemble method) (QApproximatorSimple method) (QLambda method) (QLearning method) (QNetwork method) (QuantileDQN method) (QuantileNetwork method) (Rainbow method) (RainbowNetwork method) (RandomFourierBasis method) (Reach method) (RecurrentActorNetwork method) (RecurrentCriticNetwork method) (RecurrentGaussianTorchPolicy method) (REINFORCE method) (ReplayMemory method) (REPS method) (RLearning method) (RQLearning method) (RudinPPO method) (RunningAveragedWindow method) (RunningExpWeightedAverage method) (RunningStandardization method) (RWR method) (SAC method) (SARSA method) (SARSALambda method) (SARSALambdaContinuous method) (Segway method) (SequenceReplayMemory method) (SGDOptimizer method) (ShipSteering method) (SilverBadgerWalking method) (SpeedyQLearning method) (SquashedGaussian method) (SquashedGaussianTorchPolicy method) (StandardizationPreprocessor method) (StatefulPolicy method) (StateLogStdGaussianPolicy method) (StateStdGaussianPolicy method) (StochasticAC method) (StochasticAC_AVG method) (Table method) (TD3 method) (TDPolicy method) (Tiles method) (TorchApproximator method) (TorchEnsemble method) (TorchTrainer method) (TRPO method) (TrueOnlineSARSALambda method) (VarianceParameter method) (VectorizedDataset method) (VectorPolicy method) (VideoLogger method) (VideoRecorder method) (Viewer method) (VoronoiTiles method) (Walker2D method) (WandbLogger method) (WeightedQLearning method) (WindowedVarianceParameter method)

_add_logger_attr() (MushroomObject method) _add_save_attr() (MushroomObject method) _affected_window() (ReplayMemory method) _agent_preprocess() (Agent method) _apply_carb_settings() (IsaacSim method) _assemble_batch() (ReplayMemory method) _bound() (Environment method) _check_collision() (IsaacSim method) (MuJoCo method) _compute() (DecayParameter method) (LinearParameter method) (Parameter method) (VarianceParameter method) (WindowedVarianceParameter method) _compute_action() (A1Walking method) (AirHockeyBaseBullet method) (HoneyBadgerWalking method) (IsaacSim method) (MuJoCo method) (PyBullet method) _compute_exponents() (PolynomialBasis static method) _compute_gradient() (eNAC method) (GPOMDP method) (REINFORCE method) _compute_mask() (ReplayMemory method) _compute_phase() (ProMP method) _convert_to_scale() (GaussianRBFTensor static method) (GenericBasisTensor static method) (VonMisesBFTensor static method) _create_core_logic() (Core method) (SequentialCore method) (VectorizedCore method) _create_info_dictionary() (A1Walking method) (AirHockeyDouble method) (AirHockeySingle method) (Ant method) (CartPole method) (HalfCheetah method) (HoneyBadgerWalking method) (Hopper method) (IsaacSim method) (MuJoCo method) (PegInsertion method) (Pick method) (Push method) (Reach method) (Walker2D method) _create_observation() (A1Walking method) (AirHockeyDefendBullet method) (AirHockeyDouble method) (AirHockeyHitBullet method) (AirHockeyPrepareBullet method) (AirHockeyRepelBullet method) (AirHockeySingle method) (AirHockeySingleBullet method) (Ant method) (HalfCheetah method) (HoneyBadgerWalking method) (Hopper method) (IsaacSim method) (MuJoCo method) (Panda method) (PegInsertion method) (Pick method) (Push method) (PyBullet method) (Reach method) (Walker2D method) _create_simulation_app() (IsaacSim method) _create_world() (IsaacSim method) _custom_load_models() (PyBullet method) _draw_action() (DMP method) (OrnsteinUhlenbeckPolicy method) (ProMP method) (RecurrentGaussianTorchPolicy method) (StatefulPolicy method) _episode_end_update() (eNAC method) (GPOMDP method) (REINFORCE method) _get_collision_count() (IsaacSim method) _get_collision_force() (IsaacSim method) (MuJoCo method) _get_ctrl_cost() (Hopper method) (Walker2D method) _get_env_id_map() (MultiMuJoCo static method) _get_folder() (DataLogger method) _get_healthy_reward() (Hopper method) (Walker2D method) _get_net_collision_forces() (IsaacSim method) _init_update() (eNAC method) (GPOMDP method) (REINFORCE method) _is_healthy() (Hopper method) _is_within_angle_range() (Hopper method) (Walker2D method) _is_within_state_range() (Hopper method) _is_within_z_range() (Hopper method) (Walker2D method) _modify_mdp_info() (AirHockeySingleBullet method) (Ant method) (HalfCheetah method) (Hopper method) (IsaacSim method) (MuJoCo method) (Panda method) (PegInsertion method) (Pick method) (Push method) (PyBullet method) (Reach method) (Walker2D method) _modify_observation() (A1Walking method) (AirHockeyDouble method) (AirHockeySingle method) (HoneyBadgerWalking method) (IsaacSim method) (MuJoCo method) _next_q() (AbstractDQN method) (AveragedDQN method) (DDPG method) (DoubleDQN method) (DQN method) (RQLearning method) (SAC method) (TD3 method) (WeightedQLearning method) _optimize_actor_parameters() (DeepAC method) _post_load() (MushroomObject method) _prepare_dataset() (Core method) (SequentialCore method) (VectorizedCore method) _preprocess() (Core method) _preprocess_action() (A1Walking method) (HoneyBadgerWalking method) (IsaacSim method) (MuJoCo method) (PyBullet method) _read_data() (IsaacSim method) (MuJoCo method) _reset() (SequentialCore method) (VectorizedCore method) _sample_idxs() (ReplayMemory method) _set_task() (IsaacSim method) _simulation_post_step() (AirHockeyDefendBullet method) (AirHockeyDouble method) (AirHockeyHitBullet method) (AirHockeyPrepareBullet method) (AirHockeyRepelBullet method) (AirHockeySingle method) (IsaacSim method) (MuJoCo method) (PyBullet method) _simulation_pre_step() (AirHockeyBase method) (AirHockeyBaseBullet method) (IsaacSim method) (MuJoCo method) (Panda method) (PyBullet method) _split_variables() (DMP method) _step() (SequentialCore method) (VectorizedCore method) _step_finalize() (A1Walking method) (HoneyBadgerWalking method) (IsaacSim method) (MuJoCo method) (PyBullet method) _step_init() (MuJoCo method) (PyBullet method) _step_update() (eNAC method) (GPOMDP method) (REINFORCE method) _sync_tree_mask() (PrioritizedReplayMemory method) _update() (BlackBoxOptimization method) (ConstrainedREPS method) (DoubleQLearning method) (ePPO method) (ExpectedSARSA method) (MaxminQLearning method) (MORE 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_agent_preprocessor() (Agent method) _update_target() (AbstractDQN method) (AveragedDQN method) (MaxminDQN method) _wait() (CV2Viewer method) _window_was_closed() (CV2Viewer method) _write_data() (IsaacSim method) (MuJoCo method) _write_to_buffer() (ReplayMemory method)

A

A1Walking (class in mushroom_rl.environments.isaacsim_envs.a1_walking) A2C (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) abs() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) AbstractDQN (class in mushroom_rl.algorithms.value.dqn) AbstractGaussianPolicy (class in mushroom_rl.policy.gaussian_policy) AbstractGridWorld (class in mushroom_rl.environments.grid_world) AccumulatingTrace (class in mushroom_rl.rl_utils.eligibility_trace) action_history_length (HistoryManager property) ActorNetwork (class in mushroom_rl.approximators.parametric.networks.actor_network) AdamOptimizer (class in mushroom_rl.rl_utils.optimizers) AdaptiveOptimizer (class in mushroom_rl.rl_utils.optimizers) add() (PrioritizedReplayMemory method) (ReplayMemory method) add_agent_preprocessor() (Agent method) add_core_preprocessor() (Agent method) add_stream() (HistoryManager method) advance_step() (WandbLogger method) Agent (class in mushroom_rl.core.agent) agent_array_backend (DatasetInfo property) AgentInfo (class in mushroom_rl.core.agent) AirHockeyBase (class in mushroom_rl.environments.mujoco_envs.air_hockey.base) AirHockeyBaseBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.base) AirHockeyDefend (class in mushroom_rl.environments.mujoco_envs.air_hockey.defend) AirHockeyDefendBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.defend) AirHockeyDouble (class in mushroom_rl.environments.mujoco_envs.air_hockey.double) AirHockeyHit (class in mushroom_rl.environments.mujoco_envs.air_hockey.hit) AirHockeyHitBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.hit) AirHockeyPrepare (class in mushroom_rl.environments.mujoco_envs.air_hockey.prepare)

AirHockeyPrepareBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.prepare) AirHockeyRepel (class in mushroom_rl.environments.mujoco_envs.air_hockey.repel) AirHockeyRepelBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.repel) AirHockeySingle (class in mushroom_rl.environments.mujoco_envs.air_hockey.single) AirHockeySingleBullet (class in mushroom_rl.environments.pybullet_envs.air_hockey.single) Ant (class in mushroom_rl.environments.mujoco_envs.ant) append_batch() (Dataset method) append_theta_vectorized() (VectorizedDataset method) append_vectorized() (VectorizedDataset method) Approximator (class in mushroom_rl.approximators.approximator) arange() (ArrayBackend static method) (ListBackend class method) (NumpyBackend class method) (TorchBackend class method) ArrayBackend (class in mushroom_rl.core.array_backend) arrays_to_list() (ArrayBackend class method) arrays_to_numpy() (ArrayBackend class method) arrays_to_torch() (ArrayBackend class method) arrow_head() (Viewer method) as_array() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) Atari (class in mushroom_rl.environments.atari) AtariFeatureNetwork (class in mushroom_rl.approximators.parametric.networks.atari_network) AtariNetwork (class in mushroom_rl.approximators.parametric.networks.atari_network) atleast_2d() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) AveragedDQN (class in mushroom_rl.algorithms.value.dqn)

B

background_image() (Viewer method) BallInACup (class in mushroom_rl.environments.mujoco_envs.ball_in_a_cup) bfs() (in module mushroom_rl.solvers.car_on_hill) BlackBoxOptimization (class in mushroom_rl.algorithms.policy_search.black_box_optimization) 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.core.spaces) build_history() (HistoryManager method) build_history_circular_buffer() (HistoryManager method) build_nstep_return() (HistoryManager method) build_nstep_return_circular_buffer() (HistoryManager method)

C

CarOnHill (class in mushroom_rl.environments.car_on_hill) CartPole (class in mushroom_rl.environments.cart_pole) (class in mushroom_rl.environments.isaacsim_envs.cartpole) CategoricalDQN (class in mushroom_rl.algorithms.value.dqn) CategoricalNetwork (class in mushroom_rl.approximators.parametric.networks.categorical_network) CategoricalWrapper (class in mushroom_rl.utils.torch_distributions) check_device() (ArrayBackend class method) circle() (Viewer method) cleanup() (IsaacSim method) clear() (VectorizedDataset method) clip() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) ClippedGaussianPolicy (class in mushroom_rl.policy.noise_policy) close() (ImageViewer method) (Viewer method) CMAC (class in mushroom_rl.approximators.parametric.cmac) compute_advantage() (in module mushroom_rl.rl_utils.value_functions) compute_advantage_montecarlo() (in module mushroom_rl.rl_utils.value_functions) compute_gae() (in module mushroom_rl.rl_utils.value_functions) (PPO_BPTT static method) compute_J() (Dataset method) 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() (Dataset method) 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) concatenate() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) ConsoleLogger (class in mushroom_rl.core.logger) ConstantTensor (class in mushroom_rl.features.tensors.constant_tensor) ConstrainedREPS (class in mushroom_rl.algorithms.policy_search.black_box_optimization) ContextBuilder (class in mushroom_rl.algorithms.policy_search.black_box_optimization) convert() (ArrayBackend class method) convert_to_backend() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) COPDAC_Q (class in mushroom_rl.algorithms.actor_critic.classic_actor_critic) copy() (ArrayBackend static method) (ListBackend static method) (MushroomObject method) (NumpyBackend static method) (TorchBackend static method) Core (class in mushroom_rl.core.core) core_preprocessors (Agent property) create_dataset_info() (DatasetInfo static method) create_raw_instance() (Dataset class method) create_replay_memory_info() (DatasetInfo static method) critical() (ConsoleLogger method) CriticNetwork (class in mushroom_rl.approximators.parametric.networks.critic_network) CV2Viewer (class in mushroom_rl.utils.viewer)

D

DataLogger (class in mushroom_rl.core.logger) Dataset (class in mushroom_rl.core.dataset) Dataset._Field (class in mushroom_rl.core.dataset) Dataset._PolicyField (class in mushroom_rl.core.dataset) DatasetInfo (class in mushroom_rl.core.dataset) DDPG (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) debug() (ConsoleLogger method) DecayParameter (class in mushroom_rl.rl_utils.parameters) DeepAC (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) default_streams() (HistoryManager class method) default_wandb_kwargs() (WandbLogger static method) DeterministicPolicy (class in mushroom_rl.policy.deterministic_policy) DiagonalGaussianPolicy (class in mushroom_rl.policy.gaussian_policy) diff() (CMAC method) (Distribution method) (HasGradient method) (LinearApproximator method) (NumpyTorchApproximator method) (QApproximatorAction method) (QApproximatorEnsemble method) (QApproximatorSimple method) (TorchApproximator method) (TorchEnsemble method) diff_log() (DiagonalGaussianPolicy method) (Distribution method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) (GaussianPolicy method) (HasGradient method) (StateLogStdGaussianPolicy method) (StateStdGaussianPolicy method) Discrete (class in mushroom_rl.core.spaces) display() (CV2Viewer method) (ImageViewer method) (Viewer method)

Distribution (class in mushroom_rl.distributions.distribution) distribution() (BoltzmannTorchPolicy method) (GaussianTorchPolicy method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (StatefulTorchPolicy method) (TorchPolicy method) DMControl (class in mushroom_rl.environments.dm_control_env) DMP (class in mushroom_rl.policy.dmp) 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() (AbstractGaussianPolicy method) (Agent method) (Boltzmann method) (BoltzmannTorchPolicy method) (ClippedGaussianPolicy method) (DeterministicPolicy method) (EpsGreedy method) (GaussianTorchPolicy method) (Policy method) (SquashedGaussianTorchPolicy method) (StatefulPolicy method) (VectorPolicy method) draw_with_log_prob() (BoltzmannTorchPolicy method) (GaussianTorchPolicy method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (StatefulTorchPolicy method) (TorchPolicy method) DuelingDQN (class in mushroom_rl.algorithms.value.dqn) DuelingNetwork (class in mushroom_rl.approximators.parametric.networks.dueling_network)

E

EligibilityTrace() (in module mushroom_rl.rl_utils.eligibility_trace) empty() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) eNAC (class in mushroom_rl.algorithms.policy_search.policy_gradient) Ensemble (class in mushroom_rl.approximators.approximator) ensemble_minibatch_generator() (in module mushroom_rl.utils.minibatches) entropy() (BoltzmannTorchPolicy method) (Distribution method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) (GaussianTorchPolicy method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (TorchPolicy method) env_array_backend (DatasetInfo property) Environment (class in mushroom_rl.core.environment) episode_start() (Agent method) (BlackBoxOptimization method) (QLambda method) (SARSALambda method) (SARSALambdaContinuous method) (StochasticAC method) (TrueOnlineSARSALambda method)

episode_start_vectorized() (Agent method) (BlackBoxOptimization method) episodes_length (Dataset property) epoch_info() (ConsoleLogger method) ePPO (class in mushroom_rl.algorithms.policy_search.black_box_optimization) EpsGreedy (class in mushroom_rl.policy.td_policy) error() (ConsoleLogger method) euler_to_mat() (in module mushroom_rl.utils.angles) euler_to_quat() (in module mushroom_rl.utils.angles) evaluate() (Core method) exception() (ConsoleLogger method) exp() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) expand_dims() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) ExpectedSARSA (class in mushroom_rl.algorithms.value.td) extra_repr() (NoisyNetwork.NoisyLinear method)

F

Features() (in module mushroom_rl.features.features) finish() (WandbLogger method) FiniteMDP (class in mushroom_rl.environments.finite_mdp) fit() (Agent method) flatten() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) (VectorizedDataset method) force_arrow() (Viewer method) forward() (ActorNetwork method) (AtariFeatureNetwork method) (AtariNetwork method) (CategoricalNetwork method) (CriticNetwork method) (DuelingNetwork method) (LinearNetwork method) (NoisyNetwork method) (NoisyNetwork.NoisyLinear method) (QNetwork method) (QuantileNetwork method) (RainbowNetwork method) (RecurrentActorNetwork method) (RecurrentCriticNetwork method)

FourierBasis (class in mushroom_rl.features.basis.fourier) FQI (class in mushroom_rl.algorithms.value.batch_td) from_array() (Dataset class method) from_list() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) full() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) function() (Viewer method)

G

GaussianCholeskyDistribution (class in mushroom_rl.distributions.gaussian) GaussianDiagonalDistribution (class in mushroom_rl.distributions.gaussian) GaussianDistribution (class in mushroom_rl.distributions.gaussian) GaussianPolicy (class in mushroom_rl.policy.gaussian_policy) GaussianRBF (class in mushroom_rl.features.basis.gaussian_rbf) GaussianRBFTensor (class in mushroom_rl.features.tensors.basis_tensor) GaussianTorchPolicy (class in mushroom_rl.policy.torch_policy) generate() (FourierBasis static method) (GaussianRBF static method) (GenericBasisTensor class method) (LQR static method) (PolynomialBasis static method) (RandomFourierBasis static method) (Tiles static method) (VoronoiTiles static method) generate_grid_world() (in module mushroom_rl.environments.generators.grid_world) generate_simple_chain() (in module mushroom_rl.environments.generators.simple_chain) generate_taxi() (in module mushroom_rl.environments.generators.taxi) GenericBasisTensor (class in mushroom_rl.features.tensors.basis_tensor) get() (PrioritizedReplayMemory method) (ReplayMemory method) (SequenceReplayMemory method) get_action_features() (in module mushroom_rl.features.features) get_action_indices() (MuJoCo static method) get_action_space() (MuJoCo static method) get_all_observation_keys() (MuJoCo method) get_array_backend() (ArrayBackend static method) get_array_backend_from() (ArrayBackend static method) get_backend_name() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) get_backend_serialization() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) get_ee() (AirHockeySingle method) get_frame() (Viewer static method) get_init_states() (Dataset method)

get_mean_and_confidence() (in module mushroom_rl.utils.plot) get_parameters() (Distribution method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) get_puck() (AirHockeySingle method) get_q() (TDPolicy method) get_regressor() (DeterministicPolicy method) get_sim_state() (PyBullet method) get_states() (Ant method) (Hopper method) get_value() (AdaptiveOptimizer method) (Parameter method) get_weights() (BoltzmannTorchPolicy method) (ClippedGaussianPolicy method) (DeterministicPolicy method) (DiagonalGaussianPolicy method) (DMP method) (GaussianPolicy method) (GaussianTorchPolicy method) (HasWeights method) (LinearApproximator method) (NumpyTorchApproximator method) (OrnsteinUhlenbeckPolicy method) (ProMP method) (QApproximatorAction method) (QApproximatorEnsemble method) (QApproximatorSimple method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (StateLogStdGaussianPolicy method) (StateStdGaussianPolicy method) (TorchApproximator method) (TorchEnsemble method) (TorchPolicy method) (VectorPolicy 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) Gymnasium (class in mushroom_rl.environments.gymnasium_env)

H

HalfCheetah (class in mushroom_rl.environments.mujoco_envs.half_cheetah) HasGradient (class in mushroom_rl.policy.policy) HasWeights (class in mushroom_rl.policy.policy) high (Box property) history_length (Agent property) (HistoryManager property)

history_manager (Agent property) HistoryManager (class in mushroom_rl.core.history_manager) HoneyBadgerWalking (class in mushroom_rl.environments.isaacsim_envs.honey_badger_walking) Hopper (class in mushroom_rl.environments.mujoco_envs.hopper)

I

ImageViewer (class in mushroom_rl.utils.viewer) inf() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) info (Environment property) info() (ConsoleLogger method) initial_value (Parameter property) initialized (ReplayMemory property) input_shape (Approximator property) InvertedPendulum (class in mushroom_rl.environments.inverted_pendulum) is_absorbing() (A1Walking method) (AirHockeyBase method) (AirHockeyBaseBullet method) (AirHockeyDefend method) (AirHockeyDefendBullet method) (AirHockeyHitBullet method) (AirHockeyPrepare method) (AirHockeyPrepareBullet method) (AirHockeyRepel method) (AirHockeyRepelBullet method) (Ant method) (BallInACup method) (CartPole method) (HalfCheetah method) (HoneyBadgerWalking method) (Hopper method) (IsaacSim method) (MuJoCo method) (PegInsertion method) (Pick method) (Push method) (PyBullet method) (Reach method) (Walker2D method)

is_cyclic() (GenericBasisTensor class method) (VonMisesBFTensor class method) is_stateful (Policy property) (StatefulPolicy property) IsaacSim (class in mushroom_rl.environments.isaacsim_env)

L

learn() (Core method) line() (Viewer method) LinearApproximator (class in mushroom_rl.approximators.parametric.linear) LinearNetwork (class in mushroom_rl.approximators.parametric.networks.linear_network) LinearParameter (class in mushroom_rl.rl_utils.parameters) list_registered() (Environment static method) ListBackend (class in mushroom_rl.core.array_backend) load() (MushroomObject class method) load_model() (MuJoCo static method) log_agent() (DataLogger method) log_best_agent() (DataLogger method) log_evaluation() (Logger method) log_numpy() (DataLogger method) log_numpy_array() (DataLogger method) log_pdf() (Distribution method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) log_prob() (BoltzmannTorchPolicy method) (GaussianTorchPolicy method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (StatefulTorchPolicy method) (TorchPolicy method)

log_training() (Logger method) log_video() (Logger method) log_wandb_eval() (WandbLogger method) log_wandb_training() (WandbLogger method) log_wandb_video() (WandbLogger method) Logger (class in mushroom_rl.core.logger) logical_and() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) loss_fit (TorchApproximator property) (TorchEnsemble property) low (Box property) LQR (class in mushroom_rl.environments.lqr) LSPI (class in mushroom_rl.algorithms.value.batch_td)

M

make() (Environment static method) mask (VectorizedDataset property) masked_init() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) mat_to_euler() (in module mushroom_rl.utils.angles) max() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) max_priority (PrioritizedReplayMemory property) max_reach (HistoryManager property) maximum() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) MaxminDQN (class in mushroom_rl.algorithms.value.dqn) MaxminQLearning (class in mushroom_rl.algorithms.value.td) MDPInfo (class in mushroom_rl.core.environment) mean (RunningAveragedWindow property) (RunningExpWeightedAverage property) (RunningStandardization property) median() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) Mellowmax (class in mushroom_rl.policy.td_policy) Mellowmax.MellowmaxParameter (class in mushroom_rl.policy.td_policy) min() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) minibatch_generator() (in module mushroom_rl.utils.minibatches) minibatch_number() (in module mushroom_rl.utils.minibatches) MiniGrid (class in mushroom_rl.environments.minigrid_env) MiniGridBase (class in mushroom_rl.environments.minigrid_env) MiniGridRGB (class in mushroom_rl.environments.minigrid_env) minimum() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) MinMaxPreprocessor (class in mushroom_rl.rl_utils.preprocessors) mle() (Distribution method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) model (QApproximatorAction property) (QApproximatorSimple property) module mushroom_rl.algorithms.actor_critic.classic_actor_critic mushroom_rl.algorithms.actor_critic.deep_actor_critic mushroom_rl.algorithms.policy_search.black_box_optimization mushroom_rl.algorithms.policy_search.policy_gradient mushroom_rl.algorithms.value.batch_td mushroom_rl.algorithms.value.dqn mushroom_rl.algorithms.value.td mushroom_rl.approximators.approximator mushroom_rl.approximators.parametric.cmac mushroom_rl.approximators.parametric.linear mushroom_rl.approximators.parametric.networks.actor_network mushroom_rl.approximators.parametric.networks.atari_network mushroom_rl.approximators.parametric.networks.categorical_network mushroom_rl.approximators.parametric.networks.critic_network mushroom_rl.approximators.parametric.networks.dueling_network mushroom_rl.approximators.parametric.networks.linear_network mushroom_rl.approximators.parametric.networks.noisy_network mushroom_rl.approximators.parametric.networks.q_network mushroom_rl.approximators.parametric.networks.quantile_network mushroom_rl.approximators.parametric.networks.rainbow_network mushroom_rl.approximators.parametric.networks.recurrent_network mushroom_rl.approximators.parametric.torch_approximator mushroom_rl.approximators.q_approximator mushroom_rl.approximators.table mushroom_rl.core.agent mushroom_rl.core.array_backend mushroom_rl.core.core mushroom_rl.core.dataset mushroom_rl.core.environment mushroom_rl.core.history_manager mushroom_rl.core.logger mushroom_rl.core.mushroom_object mushroom_rl.core.spaces mushroom_rl.distributions.distribution mushroom_rl.distributions.gaussian mushroom_rl.environments.car_on_hill mushroom_rl.environments.cart_pole mushroom_rl.environments.dm_control_env mushroom_rl.environments.finite_mdp mushroom_rl.environments.generators.grid_world mushroom_rl.environments.generators.simple_chain mushroom_rl.environments.generators.taxi mushroom_rl.environments.grid_world mushroom_rl.environments.gymnasium_env mushroom_rl.environments.inverted_pendulum mushroom_rl.environments.isaacsim_env mushroom_rl.environments.isaacsim_envs.a1_walking mushroom_rl.environments.isaacsim_envs.cartpole mushroom_rl.environments.isaacsim_envs.honey_badger_walking mushroom_rl.environments.isaacsim_envs.silver_badger_walking mushroom_rl.environments.lqr mushroom_rl.environments.minigrid_env mushroom_rl.environments.mujoco mushroom_rl.environments.mujoco_envs.air_hockey.base mushroom_rl.environments.mujoco_envs.air_hockey.defend mushroom_rl.environments.mujoco_envs.air_hockey.double mushroom_rl.environments.mujoco_envs.air_hockey.hit mushroom_rl.environments.mujoco_envs.air_hockey.prepare mushroom_rl.environments.mujoco_envs.air_hockey.repel mushroom_rl.environments.mujoco_envs.air_hockey.single mushroom_rl.environments.mujoco_envs.ant mushroom_rl.environments.mujoco_envs.ball_in_a_cup mushroom_rl.environments.mujoco_envs.half_cheetah mushroom_rl.environments.mujoco_envs.hopper mushroom_rl.environments.mujoco_envs.panda mushroom_rl.environments.mujoco_envs.peg_insertion mushroom_rl.environments.mujoco_envs.pick mushroom_rl.environments.mujoco_envs.push mushroom_rl.environments.mujoco_envs.reach mushroom_rl.environments.mujoco_envs.walker_2d mushroom_rl.environments.omni_isaac_gym_env mushroom_rl.environments.puddle_world mushroom_rl.environments.pybullet mushroom_rl.environments.pybullet_envs.air_hockey.base mushroom_rl.environments.pybullet_envs.air_hockey.defend mushroom_rl.environments.pybullet_envs.air_hockey.hit mushroom_rl.environments.pybullet_envs.air_hockey.prepare mushroom_rl.environments.pybullet_envs.air_hockey.repel mushroom_rl.environments.pybullet_envs.air_hockey.single mushroom_rl.environments.segway mushroom_rl.environments.ship_steering mushroom_rl.features._implementations.features_implementation mushroom_rl.features.basis.fourier mushroom_rl.features.basis.gaussian_rbf mushroom_rl.features.basis.polynomial mushroom_rl.features.features mushroom_rl.features.tensors.basis_tensor mushroom_rl.features.tensors.constant_tensor mushroom_rl.features.tensors.random_fourier_tensor mushroom_rl.features.tiles.tiles mushroom_rl.features.tiles.voronoi mushroom_rl.policy.deterministic_policy mushroom_rl.policy.dmp mushroom_rl.policy.gaussian_policy mushroom_rl.policy.noise_policy mushroom_rl.policy.policy mushroom_rl.policy.promps mushroom_rl.policy.stateful_torch_policy mushroom_rl.policy.td_policy mushroom_rl.policy.torch_policy mushroom_rl.policy.vector_policy mushroom_rl.rl_utils.eligibility_trace mushroom_rl.rl_utils.optimizers mushroom_rl.rl_utils.parameters mushroom_rl.rl_utils.preprocessors mushroom_rl.rl_utils.replay_memory mushroom_rl.rl_utils.running_stats mushroom_rl.rl_utils.value_functions mushroom_rl.rl_utils.variance_parameters mushroom_rl.solvers.car_on_hill mushroom_rl.solvers.dynamic_programming mushroom_rl.solvers.lqr mushroom_rl.utils.angles mushroom_rl.utils.features mushroom_rl.utils.minibatches mushroom_rl.utils.numerical_gradient mushroom_rl.utils.plot mushroom_rl.utils.record mushroom_rl.utils.torch_distributions mushroom_rl.utils.torch_training mushroom_rl.utils.torch_utils mushroom_rl.utils.viewer MORE (class in mushroom_rl.algorithms.policy_search.black_box_optimization) MuJoCo (class in mushroom_rl.environments.mujoco) MultiMuJoCo (class in mushroom_rl.environments.mujoco) multinomial() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) 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.approximator module mushroom_rl.approximators.parametric.cmac module mushroom_rl.approximators.parametric.linear module mushroom_rl.approximators.parametric.networks.actor_network module mushroom_rl.approximators.parametric.networks.atari_network module mushroom_rl.approximators.parametric.networks.categorical_network module mushroom_rl.approximators.parametric.networks.critic_network module mushroom_rl.approximators.parametric.networks.dueling_network module mushroom_rl.approximators.parametric.networks.linear_network module mushroom_rl.approximators.parametric.networks.noisy_network module

mushroom_rl.approximators.parametric.networks.q_network module mushroom_rl.approximators.parametric.networks.quantile_network module mushroom_rl.approximators.parametric.networks.rainbow_network module mushroom_rl.approximators.parametric.networks.recurrent_network module mushroom_rl.approximators.parametric.torch_approximator module mushroom_rl.approximators.q_approximator module mushroom_rl.approximators.table module mushroom_rl.core.agent module mushroom_rl.core.array_backend module mushroom_rl.core.core module mushroom_rl.core.dataset module mushroom_rl.core.environment module mushroom_rl.core.history_manager module mushroom_rl.core.logger module mushroom_rl.core.mushroom_object module mushroom_rl.core.spaces module mushroom_rl.distributions.distribution module mushroom_rl.distributions.gaussian module mushroom_rl.environments.car_on_hill module mushroom_rl.environments.cart_pole module mushroom_rl.environments.dm_control_env module mushroom_rl.environments.finite_mdp module mushroom_rl.environments.generators.grid_world module mushroom_rl.environments.generators.simple_chain module mushroom_rl.environments.generators.taxi module mushroom_rl.environments.grid_world module mushroom_rl.environments.gymnasium_env module mushroom_rl.environments.inverted_pendulum module mushroom_rl.environments.isaacsim_env module mushroom_rl.environments.isaacsim_envs.a1_walking module mushroom_rl.environments.isaacsim_envs.cartpole module mushroom_rl.environments.isaacsim_envs.honey_badger_walking module mushroom_rl.environments.isaacsim_envs.silver_badger_walking module mushroom_rl.environments.lqr module mushroom_rl.environments.minigrid_env module mushroom_rl.environments.mujoco module mushroom_rl.environments.mujoco_envs.air_hockey.base module mushroom_rl.environments.mujoco_envs.air_hockey.defend module mushroom_rl.environments.mujoco_envs.air_hockey.double module mushroom_rl.environments.mujoco_envs.air_hockey.hit module mushroom_rl.environments.mujoco_envs.air_hockey.prepare module mushroom_rl.environments.mujoco_envs.air_hockey.repel module mushroom_rl.environments.mujoco_envs.air_hockey.single module mushroom_rl.environments.mujoco_envs.ant module mushroom_rl.environments.mujoco_envs.ball_in_a_cup module mushroom_rl.environments.mujoco_envs.half_cheetah module mushroom_rl.environments.mujoco_envs.hopper module mushroom_rl.environments.mujoco_envs.panda module mushroom_rl.environments.mujoco_envs.peg_insertion module mushroom_rl.environments.mujoco_envs.pick module mushroom_rl.environments.mujoco_envs.push module mushroom_rl.environments.mujoco_envs.reach module mushroom_rl.environments.mujoco_envs.walker_2d module mushroom_rl.environments.omni_isaac_gym_env module mushroom_rl.environments.puddle_world module mushroom_rl.environments.pybullet module mushroom_rl.environments.pybullet_envs.air_hockey.base module mushroom_rl.environments.pybullet_envs.air_hockey.defend module mushroom_rl.environments.pybullet_envs.air_hockey.hit module mushroom_rl.environments.pybullet_envs.air_hockey.prepare module mushroom_rl.environments.pybullet_envs.air_hockey.repel module mushroom_rl.environments.pybullet_envs.air_hockey.single module mushroom_rl.environments.segway module mushroom_rl.environments.ship_steering module mushroom_rl.features._implementations.features_implementation module mushroom_rl.features.basis.fourier module mushroom_rl.features.basis.gaussian_rbf module mushroom_rl.features.basis.polynomial module mushroom_rl.features.features module mushroom_rl.features.tensors.basis_tensor module mushroom_rl.features.tensors.constant_tensor module mushroom_rl.features.tensors.random_fourier_tensor module mushroom_rl.features.tiles.tiles module mushroom_rl.features.tiles.voronoi module mushroom_rl.policy.deterministic_policy module mushroom_rl.policy.dmp module mushroom_rl.policy.gaussian_policy module mushroom_rl.policy.noise_policy module mushroom_rl.policy.policy module mushroom_rl.policy.promps module mushroom_rl.policy.stateful_torch_policy module mushroom_rl.policy.td_policy module mushroom_rl.policy.torch_policy module mushroom_rl.policy.vector_policy module mushroom_rl.rl_utils.eligibility_trace module mushroom_rl.rl_utils.optimizers module mushroom_rl.rl_utils.parameters module mushroom_rl.rl_utils.preprocessors module mushroom_rl.rl_utils.replay_memory module mushroom_rl.rl_utils.running_stats module mushroom_rl.rl_utils.value_functions module mushroom_rl.rl_utils.variance_parameters module mushroom_rl.solvers.car_on_hill module mushroom_rl.solvers.dynamic_programming module mushroom_rl.solvers.lqr module mushroom_rl.utils.angles module mushroom_rl.utils.features module mushroom_rl.utils.minibatches module mushroom_rl.utils.numerical_gradient module mushroom_rl.utils.plot module mushroom_rl.utils.record module mushroom_rl.utils.torch_distributions module mushroom_rl.utils.torch_training module mushroom_rl.utils.torch_utils module mushroom_rl.utils.viewer module MushroomObject (class in mushroom_rl.core.mushroom_object)

N

n_actions (Ensemble property) (Table property) network (TorchEnsemble property) NoisyDQN (class in mushroom_rl.algorithms.value.dqn) NoisyNetwork (class in mushroom_rl.approximators.parametric.networks.noisy_network) NoisyNetwork.NoisyLinear (class in mushroom_rl.approximators.parametric.networks.noisy_network) none() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) nonzero() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method)

norm() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) normalize_angle() (in module mushroom_rl.utils.angles) normalize_angle_positive() (in module mushroom_rl.utils.angles) nstep_valid() (HistoryManager method) nstep_valid_circular_buffer() (HistoryManager method) 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) NumpyBackend (class in mushroom_rl.core.array_backend) NumpyTorchApproximator (class in mushroom_rl.approximators.parametric.torch_approximator)

O

OmniIsaacGymEnv (class in mushroom_rl.environments.omni_isaac_gym_env) ones() (ArrayBackend class method) (ListBackend class method) (NumpyBackend class method) (TorchBackend class method) ones_like() (ArrayBackend class method) (ListBackend class method) (NumpyBackend class method) (TorchBackend class method)

OnPolicyDeepAC (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) Optimizer (class in mushroom_rl.rl_utils.optimizers) OrnsteinUhlenbeckPolicy (class in mushroom_rl.policy.noise_policy) output_shape (Approximator property)

P

pack_padded_sequence() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) Panda (class in mushroom_rl.environments.mujoco_envs.panda) Parameter (class in mushroom_rl.rl_utils.parameters) parameters() (BoltzmannTorchPolicy method) (GaussianTorchPolicy method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (TorchApproximator method) (TorchEnsemble method) (TorchPolicy method) parameters_size (Distribution property) (GaussianCholeskyDistribution property) (GaussianDiagonalDistribution property) (GaussianDistribution property) parse() (Dataset method) parse_grid() (in module mushroom_rl.environments.generators.grid_world) (in module mushroom_rl.environments.generators.taxi) parse_history() (HistoryManager method) parse_history_circular_buffer() (HistoryManager method) parse_nstep_history() (HistoryManager method) parse_nstep_history_circular_buffer() (HistoryManager method) parse_policy_state() (Dataset method) path (DataLogger property) PegInsertion (class in mushroom_rl.environments.mujoco_envs.peg_insertion)

PGPE (class in mushroom_rl.algorithms.policy_search.black_box_optimization) Pick (class in mushroom_rl.environments.mujoco_envs.pick) plot_mean_conf() (in module mushroom_rl.utils.plot) Policy (class in mushroom_rl.policy.policy) policy_iteration() (in module mushroom_rl.solvers.dynamic_programming) policy_state (Agent property) (StatefulPolicy property) polygon() (Viewer method) PolynomialBasis (class in mushroom_rl.features.basis.polynomial) PPO (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) PPO_BPTT (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) predict() (Approximator method) (CMAC method) (Ensemble method) (LinearApproximator method) (NumpyTorchApproximator method) (QApproximatorAction method) (QApproximatorSimple method) (Table method) (TorchApproximator method) (TorchEnsemble method) Preprocessor (class in mushroom_rl.rl_utils.preprocessors) PrioritizedReplayMemory (class in mushroom_rl.rl_utils.replay_memory) ProMP (class in mushroom_rl.policy.promps) PuddleWorld (class in mushroom_rl.environments.puddle_world) Push (class in mushroom_rl.environments.mujoco_envs.push) PyBullet (class in mushroom_rl.environments.pybullet)

Q

QApproximator (class in mushroom_rl.approximators.q_approximator) QApproximatorAction (class in mushroom_rl.approximators.q_approximator) QApproximatorEnsemble (class in mushroom_rl.approximators.q_approximator) QApproximatorSimple (class in mushroom_rl.approximators.q_approximator) QLambda (class in mushroom_rl.algorithms.value.td)

QLearning (class in mushroom_rl.algorithms.value.td) QNetwork (class in mushroom_rl.approximators.parametric.networks.q_network) QuantileDQN (class in mushroom_rl.algorithms.value.dqn) QuantileNetwork (class in mushroom_rl.approximators.parametric.networks.quantile_network) quat_to_euler() (in module mushroom_rl.utils.angles)

R

Rainbow (class in mushroom_rl.algorithms.value.dqn) RainbowNetwork (class in mushroom_rl.approximators.parametric.networks.rainbow_network) rand() (ArrayBackend static method) (ListBackend class method) (NumpyBackend class method) (TorchBackend static method) randint() (ArrayBackend static method) (ListBackend class method) (NumpyBackend class method) (TorchBackend static method) RandomFourierBasis (class in mushroom_rl.features.tensors.random_fourier_tensor) Reach (class in mushroom_rl.environments.mujoco_envs.reach) record_action() (HistoryManager method) record_frame() (VideoLogger method) recorded_videos (VideoLogger property) RecurrentActorNetwork (class in mushroom_rl.approximators.parametric.networks.recurrent_network) RecurrentCriticNetwork (class in mushroom_rl.approximators.parametric.networks.recurrent_network) RecurrentGaussianTorchPolicy (class in mushroom_rl.policy.stateful_torch_policy) register() (Environment class method) REINFORCE (class in mushroom_rl.algorithms.policy_search.policy_gradient) render() (AbstractGridWorld method) (Atari method) (CarOnHill method) (CartPole method) (DMControl method) (Environment method) (Gymnasium method) (InvertedPendulum method) (MuJoCo method) (PuddleWorld method) (PyBullet method) (Segway method) (ShipSteering method) render_all() (IsaacSim method) (OmniIsaacGymEnv method) repeat() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) ReplacingTrace (class in mushroom_rl.rl_utils.eligibility_trace) ReplayMemory (class in mushroom_rl.rl_utils.replay_memory) REPS (class in mushroom_rl.algorithms.policy_search.black_box_optimization) reset() (AbstractGridWorld method) (AccumulatingTrace method) (Atari method) (CarOnHill method) (CartPole method) (DMControl method) (DMP method) (Ensemble method) (Environment method) (FiniteMDP method) (Gymnasium method) (HistoryManager method) (InvertedPendulum method) (LQR method) (MiniGridBase method) (MuJoCo method) (MultiMuJoCo method) (OrnsteinUhlenbeckPolicy method) (Policy method) (PrioritizedReplayMemory method) (ProMP method) (PuddleWorld method) (PyBullet method) (QApproximatorAction method) (QApproximatorSimple method) (RecurrentGaussianTorchPolicy method) (ReplacingTrace method) (ReplayMemory method) (RunningAveragedWindow method) (RunningExpWeightedAverage method) (RunningStandardization method) (Segway method) (ShipSteering method) (StatefulPolicy method) (VectorPolicy method)

reset_all() (IsaacSim method) (OmniIsaacGymEnv method) reset_vectorized() (DMP method) (HistoryManager method) (OrnsteinUhlenbeckPolicy method) (Policy method) (ProMP method) (RecurrentGaussianTorchPolicy method) (StatefulPolicy method) (VectorPolicy method) reward() (A1Walking method) (AirHockeyDefend method) (AirHockeyDefendBullet method) (AirHockeyDouble method) (AirHockeyHit method) (AirHockeyHitBullet method) (AirHockeyPrepare method) (AirHockeyPrepareBullet method) (AirHockeyRepel method) (AirHockeyRepelBullet method) (Ant method) (BallInACup method) (CartPole method) (HalfCheetah method) (HoneyBadgerWalking method) (Hopper method) (IsaacSim method) (MuJoCo method) (PegInsertion method) (Pick method) (Push method) (PyBullet method) (Reach method) (Walker2D method) RLearning (class in mushroom_rl.algorithms.value.td) RQLearning (class in mushroom_rl.algorithms.value.td) rsample_and_log_prob() (SquashedGaussian method) RudinPPO (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) RunningAveragedWindow (class in mushroom_rl.rl_utils.running_stats) RunningExpWeightedAverage (class in mushroom_rl.rl_utils.running_stats) RunningStandardization (class in mushroom_rl.rl_utils.running_stats) 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() (MushroomObject method) save_zip() (MushroomObject method) screen (Viewer property) seed() (Atari method) (Environment method) (Gymnasium method) (IsaacSim method) (MuJoCo method) (OmniIsaacGymEnv method) (PyBullet method) Segway (class in mushroom_rl.environments.segway) select_first_episodes() (Dataset method) select_random_samples() (Dataset method) SequenceReplayMemory (class in mushroom_rl.rl_utils.replay_memory) SequentialCore (class in mushroom_rl.core.core) set_beta() (Boltzmann method) (Mellowmax method) set_duration() (ProMP method) set_epsilon() (EpsGreedy method) set_learning_rate() (TorchApproximator method) (TorchEnsemble method) set_logger() (Core method) (Ensemble method) (MushroomObject method) set_parameters() (Distribution method) (GaussianCholeskyDistribution method) (GaussianDiagonalDistribution method) (GaussianDistribution method) set_q() (TDPolicy method) set_sigma() (GaussianPolicy method) set_std() (DiagonalGaussianPolicy method) set_video_fps() (VideoLogger method) set_weights() (BoltzmannTorchPolicy method) (ClippedGaussianPolicy method) (DeterministicPolicy method) (DiagonalGaussianPolicy method) (DMP method) (GaussianPolicy method) (GaussianTorchPolicy method) (HasWeights method) (LinearApproximator method) (NumpyTorchApproximator method) (OrnsteinUhlenbeckPolicy method) (ProMP method) (QApproximatorAction method) (QApproximatorEnsemble method) (QApproximatorSimple method) (RecurrentGaussianTorchPolicy method) (SquashedGaussianTorchPolicy method) (StateLogStdGaussianPolicy method) (StateStdGaussianPolicy method) (TorchApproximator method) (TorchEnsemble method) (TorchPolicy method) (VectorPolicy method) setup() (A1Walking method) (AirHockeyDefend method) (AirHockeyDefendBullet method) (AirHockeyDouble method) (AirHockeyHit method) (AirHockeyHitBullet method) (AirHockeyPrepare method) (AirHockeyPrepareBullet method) (AirHockeyRepel method) (AirHockeyRepelBullet method) (AirHockeySingle method) (Ant method) (BallInACup method) (CartPole method) (HalfCheetah method) (HoneyBadgerWalking method) (Hopper method) (IsaacSim method) (MuJoCo method) (Panda method) (PegInsertion method) (Pick method) (Push method) (PyBullet method) (Reach method) (Walker2D method) SGDOptimizer (class in mushroom_rl.rl_utils.optimizers)

shape (Box property) (Discrete property) (MDPInfo property) (Parameter property) (Table property) shape() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) ShipSteering (class in mushroom_rl.environments.ship_steering) shortest_angular_distance() (in module mushroom_rl.utils.angles) SilverBadgerWalking (class in mushroom_rl.environments.isaacsim_envs.silver_badger_walking) size (Discrete property) (ImageViewer property) (MDPInfo property) (ReplayMemory property) (Viewer property) size() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) solve_car_on_hill() (in module mushroom_rl.solvers.car_on_hill) SpeedyQLearning (class in mushroom_rl.algorithms.value.td) sqrt() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) square() (Viewer method) SquashedGaussian (class in mushroom_rl.utils.torch_distributions) SquashedGaussianTorchPolicy (class in mushroom_rl.policy.torch_policy) squeeze() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) stack() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) StandardizationPreprocessor (class in mushroom_rl.rl_utils.preprocessors) StatefulPolicy (class in mushroom_rl.policy.policy) StatefulTorchPolicy (class in mushroom_rl.policy.stateful_torch_policy) StateLogStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy) StateStdGaussianPolicy (class in mushroom_rl.policy.gaussian_policy) std (RunningStandardization property) step() (AbstractGridWorld method) (Atari method) (CarOnHill method) (CartPole method) (DMControl method) (Environment method) (FiniteMDP method) (Gymnasium method) (in module mushroom_rl.solvers.car_on_hill) (InvertedPendulum method) (LQR method) (MiniGridBase method) (MuJoCo method) (PuddleWorld method) (PyBullet method) (Segway method) (ShipSteering method) step_all() (IsaacSim method) (OmniIsaacGymEnv 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() (AbstractGridWorld method) (Agent method) (Atari method) (CarOnHill method) (CartPole method) (DMControl method) (Environment method) (Gymnasium method) (InvertedPendulum method) (IsaacSim method) (MuJoCo method) (OmniIsaacGymEnv method) (Policy method) (PuddleWorld method) (PyBullet method) (Segway method) (ShipSteering method) (StatefulPolicy method) (VectorPolicy method) (VideoRecorder method) stop_recording() (VideoLogger method) strong_line() (ConsoleLogger method) sum() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method)

T

Table (class in mushroom_rl.approximators.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_backend() (Dataset method) to_backend_dtype() (ArrayBackend static method) (ListBackend static method) (NumpyBackend class method) (TorchBackend class method) to_list() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) to_numpy() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method)

to_torch() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) TorchApproximator (class in mushroom_rl.approximators.parametric.torch_approximator) TorchBackend (class in mushroom_rl.core.array_backend) TorchEnsemble (class in mushroom_rl.approximators.parametric.torch_approximator) TorchPolicy (class in mushroom_rl.policy.torch_policy) TorchTrainer (class in mushroom_rl.utils.torch_training) torque_arrow() (Viewer method) TRPO (class in mushroom_rl.algorithms.actor_critic.deep_actor_critic) TrueOnlineSARSALambda (class in mushroom_rl.algorithms.value.td)

U

uniform() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) uniform_grid() (in module mushroom_rl.utils.features) update() (AccumulatingTrace method) (Boltzmann method) (EpsGreedy method) (Mellowmax method) (Parameter method) (Preprocessor method) (PrioritizedReplayMemory method) (ReplacingTrace method) (StandardizationPreprocessor method) (VarianceParameter method) (WindowedVarianceParameter method)

update_stats() (RunningAveragedWindow method) (RunningExpWeightedAverage method) (RunningStandardization method) update_system() (DMP method) update_time() (ProMP method) user_warning_raise_exception() (MuJoCo static method) uses_action (HistoryManager property)

V

value_iteration() (in module mushroom_rl.solvers.dynamic_programming) VarianceDecreasingParameter (class in mushroom_rl.rl_utils.variance_parameters) VarianceIncreasingParameter (class in mushroom_rl.rl_utils.variance_parameters) VarianceParameter (class in mushroom_rl.rl_utils.variance_parameters) VectorizedCore (class in mushroom_rl.core.core) VectorizedDataset (class in mushroom_rl.core.dataset)

VectorPolicy (class in mushroom_rl.policy.vector_policy) video_recorder (VideoLogger property) VideoLogger (class in mushroom_rl.core.logger) VideoRecorder (class in mushroom_rl.utils.record) Viewer (class in mushroom_rl.utils.viewer) VonMisesBFTensor (class in mushroom_rl.features.tensors.basis_tensor) VoronoiTiles (class in mushroom_rl.features.tiles.voronoi)

W

Walker2D (class in mushroom_rl.environments.mujoco_envs.walker_2d) wandb_active (WandbLogger property) WandbLogger (class in mushroom_rl.core.logger) warning() (ConsoleLogger method) weak_line() (ConsoleLogger method) WeightedQLearning (class in mushroom_rl.algorithms.value.td) weights_size (ClippedGaussianPolicy property) (DeterministicPolicy property) (DiagonalGaussianPolicy property) (DMP property) (GaussianPolicy property) (HasWeights property) (LinearApproximator property) (OrnsteinUhlenbeckPolicy property) (ProMP property) (QApproximatorAction property) (QApproximatorEnsemble property) (QApproximatorSimple property) (StateLogStdGaussianPolicy property) (StateStdGaussianPolicy property) (TorchApproximator property) (TorchEnsemble property) (VectorPolicy property)

where() (ArrayBackend static method) (ListBackend static method) (NumpyBackend static method) (TorchBackend static method) WindowedVarianceIncreasingParameter (class in mushroom_rl.rl_utils.variance_parameters) WindowedVarianceParameter (class in mushroom_rl.rl_utils.variance_parameters)

Z

zeros() (ArrayBackend class method) (ListBackend class method) (NumpyBackend class method) (TorchBackend class method)

zeros_like() (ArrayBackend class method) (ListBackend class method) (NumpyBackend class method) (TorchBackend class method)