Index

A

a_loss_fn() (DDPG static method) a_net_state (DDPGState attribute) a_net_state_target (DDPGState attribute) a_opt_state (DDPGState attribute) a_params (DDPGState attribute) a_params_target (DDPGState attribute) action_space (BaseAgent property) (DDPG property) (DDQN property) (DQN property) (EGreedy property) (Evosax property) (Exp3 property) (ExpectedSarsa property) (NormalThompsonSampling property) (PPOContinuous property) (PPODiscrete property) (RandomScheduler property) (RLib property) (RoundRobinScheduler property) (Softmax property) (ThompsonSampling property) (UCB property)

actions (ReplayBuffer attribute) add_logger() (LogsObserver method) affine_transition() (in module reinforced_lib.utils.particle_filter) AgentState (class in reinforced_lib.agents.base_agent) alpha (NormalThompsonSamplingState attribute) (ThompsonSamplingState attribute) append (ExperienceReplay attribute)

B

BaseAgent (class in reinforced_lib.agents.base_agent) BaseExt (class in reinforced_lib.exts.base_ext) BaseLogger (class in reinforced_lib.logs.base_logger)

BasicMab (class in reinforced_lib.exts.basic_mab) best_params (EvosaxState attribute) beta (NormalThompsonSamplingState attribute) (ThompsonSamplingState attribute)

C

counter (EvosaxState attribute) (PPOState attribute)

CsvLogger (class in reinforced_lib.logs.csv_logger)

D

DDPG (class in reinforced_lib.agents.deep.ddpg) DDPGState (class in reinforced_lib.agents.deep.ddpg) DDQN (class in reinforced_lib.agents.deep.ddqn)

DDQNState (class in reinforced_lib.agents.deep.ddqn) DQN (class in reinforced_lib.agents.deep.dqn) DQNState (class in reinforced_lib.agents.deep.dqn)

E

e (EGreedyState attribute) effective_sample_size() (in module reinforced_lib.utils.particle_filter) EGreedy (class in reinforced_lib.agents.mab.e_greedy) EGreedyState (class in reinforced_lib.agents.mab.e_greedy) epsilon (DDQNState attribute) (DQNState attribute) es_state (EvosaxState attribute) Evosax (class in reinforced_lib.agents.neuro.evosax)

EvosaxState (class in reinforced_lib.agents.neuro.evosax) Exp3 (class in reinforced_lib.agents.mab.exp3) Exp3State (class in reinforced_lib.agents.mab.exp3) ExpectedSarsa (class in reinforced_lib.agents.deep.expected_sarsa) ExpectedSarsaState (class in reinforced_lib.agents.deep.expected_sarsa) experience_replay() (in module reinforced_lib.utils.experience_replay) ExperienceReplay (class in reinforced_lib.utils.experience_replay) export() (BaseAgent method)

F

finish() (BaseLogger method) (CsvLogger method) (PlotsLogger method) (RLib method) (StdoutLogger method) (TensorboardLogger method) (WeightsAndBiasesLogger method)

finish_loggers() (LogsObserver method) fitness (EvosaxState attribute) ForbiddenAgentChangeError ForbiddenExtensionChangeError ForbiddenExtensionSetError ForbiddenLoggerSetError ForbiddenOperationError forward() (in module reinforced_lib.utils.jax_utils)

G

get_agent_params() (BaseExt method) gradient_step() (in module reinforced_lib.utils.jax_utils)

Gymnasium (class in reinforced_lib.exts.gymnasium) GymnasiumVectorized (class in reinforced_lib.exts.gymnasium_vectorized)

H

H (SoftmaxState attribute)

I

IncompatibleSpacesError IncorrectAgentTypeError IncorrectExtensionTypeError IncorrectLoggerTypeError IncorrectSourceTypeError IncorrectSpaceError IncorrectTypeError init (ExperienceReplay attribute) init() (BaseAgent static method) (BaseLogger method) (DDPG static method) (DDQN static method) (DQN static method) (EGreedy static method) (Evosax static method) (Exp3 static method) (ExpectedSarsa static method) (in module reinforced_lib.utils.jax_utils) (Masked static method) (NormalThompsonSampling static method) (ParticleFilter static method) (PPODiscrete static method) (RandomScheduler static method) (RLib method) (RoundRobinScheduler static method) (Softmax static method) (ThompsonSampling static method) (UCB static method)

init_loggers() (LogsObserver method) inverse_gamma() (NormalThompsonSampling static method) is_ready (ExperienceReplay attribute) item (RoundRobinSchedulerState attribute) items() (AgentState method) (DDPGState method) (DDQNState method) (DQNState method) (EGreedyState method) (EvosaxState method) (Exp3State method) (ExpectedSarsaState method) (ExperienceReplay method) (MaskedState method) (NormalThompsonSamplingState method) (ParticleFilterState method) (PPOState method) (RandomSchedulerState method) (ReplayBuffer method) (RoundRobinSchedulerState method) (SoftmaxState method) (ThompsonSamplingState method) (UCBState method)

K

keys() (AgentState method) (DDPGState method) (DDQNState method) (DQNState method) (EGreedyState method) (EvosaxState method) (Exp3State method) (ExpectedSarsaState method) (ExperienceReplay method) (MaskedState method) (NormalThompsonSamplingState method) (ParticleFilterState method) (PPOState method) (RandomSchedulerState method) (ReplayBuffer method) (RoundRobinSchedulerState method) (SoftmaxState method) (ThompsonSamplingState method) (UCBState method)

L

lam (NormalThompsonSamplingState attribute) linear_transition() (in module reinforced_lib.utils.particle_filter) load() (RLib static method) log() (RLib method) log_array() (BaseLogger method) (CsvLogger method) (PlotsLogger method) (StdoutLogger method) (TensorboardLogger method) (WeightsAndBiasesLogger method) log_dict() (BaseLogger method) (CsvLogger method) (StdoutLogger method) (TensorboardLogger method) (WeightsAndBiasesLogger method) log_other() (BaseLogger method) (CsvLogger method) (StdoutLogger method) (TensorboardLogger method) (WeightsAndBiasesLogger method)

log_scalar() (BaseLogger method) (CsvLogger method) (PlotsLogger method) (StdoutLogger method) (TensorboardLogger method) (WeightsAndBiasesLogger method) logit_weights (ParticleFilterState attribute) LogNormalThompsonSampling (class in reinforced_lib.agents.mab.lognormal_thompson_sampling) LogsObserver (class in reinforced_lib.logs.logs_observer) loss_fn() (DDQN static method) (DQN static method) (ExpectedSarsa static method) (PPOContinuous static method) (PPODiscrete static method)

M

Masked (class in reinforced_lib.experimental.masked) MaskedState (class in reinforced_lib.experimental.masked) module reinforced_lib.utils.exceptions reinforced_lib.utils.experience_replay reinforced_lib.utils.jax_utils reinforced_lib.utils.particle_filter

mu (NormalThompsonSamplingState attribute)

N

N (EGreedyState attribute) n (SoftmaxState attribute) N (UCBState attribute) net_state (DDQNState attribute) (DQNState attribute) (ExpectedSarsaState attribute) (PPOState attribute)

net_state_target (DDQNState attribute) next_states (ReplayBuffer attribute) NoAgentError NoDefaultParameterError NoExtensionError noise (DDPGState attribute) NormalThompsonSampling (class in reinforced_lib.agents.mab.normal_thompson_sampling) NormalThompsonSamplingState (class in reinforced_lib.agents.mab.normal_thompson_sampling)

O

observation_space (BaseExt property) (RLib property) omega (Exp3State attribute)

opt_state (DDQNState attribute) (DQNState attribute) (ExpectedSarsaState attribute) (PPOState attribute)

P

parameter_space() (BaseAgent static method) (DDPG static method) (DDQN static method) (DQN static method) (EGreedy static method) (Evosax static method) (Exp3 static method) (ExpectedSarsa static method) (NormalThompsonSampling static method) (PPOContinuous static method) (PPODiscrete static method) (RandomScheduler static method) (RoundRobinScheduler static method) (Softmax static method) (ThompsonSampling static method) (UCB static method) params (DDQNState attribute) (DQNState attribute) (ExpectedSarsaState attribute) (PPOState attribute)

params_target (DDQNState attribute) ParticleFilter (class in reinforced_lib.utils.particle_filter) ParticleFilterState (class in reinforced_lib.utils.particle_filter) PlotsLogger (class in reinforced_lib.logs.plots_logger) population (EvosaxState attribute) positions (ParticleFilterState attribute) PPOContinuous (class in reinforced_lib.agents.deep.ppo_continuous) PPODiscrete (class in reinforced_lib.agents.deep.ppo_discrete) PPOState (class in reinforced_lib.agents.deep.ppo_discrete) prev_env_state (DDPGState attribute) (DDQNState attribute) (DQNState attribute) (ExpectedSarsaState attribute) prev_env_states (PPOState attribute) ptr (ReplayBuffer attribute)

Q

Q (EGreedyState attribute) q_loss_fn() (DDPG static method) q_net_state (DDPGState attribute)

q_net_state_target (DDPGState attribute) q_opt_state (DDPGState attribute) q_params (DDPGState attribute) q_params_target (DDPGState attribute)

R

r (SoftmaxState attribute) R (UCBState attribute) RandomScheduler (class in reinforced_lib.agents.mab.scheduler.random) RandomSchedulerState (class in reinforced_lib.agents.mab.scheduler.random) reinforced_lib.utils.exceptions module reinforced_lib.utils.experience_replay module reinforced_lib.utils.jax_utils module reinforced_lib.utils.particle_filter module

replay_buffer (DDPGState attribute) (DDQNState attribute) (DQNState attribute) (ExpectedSarsaState attribute) ReplayBuffer (class in reinforced_lib.utils.experience_replay) rewards (ReplayBuffer attribute) RLib (class in reinforced_lib.rlib) rollout_memory (PPOState attribute) RoundRobinScheduler (class in reinforced_lib.agents.mab.scheduler.round_robin) RoundRobinSchedulerState (class in reinforced_lib.agents.mab.scheduler.round_robin)

S

sample (ExperienceReplay attribute) sample() (BaseAgent static method) (DDPG static method) (DDQN static method) (DQN static method) (EGreedy static method) (Evosax static method) (Exp3 static method) (ExpectedSarsa static method) (LogNormalThompsonSampling static method) (Masked static method) (NormalThompsonSampling static method) (ParticleFilter static method) (PPOContinuous static method) (PPODiscrete static method) (RandomScheduler static method) (RLib method) (RoundRobinScheduler static method) (Softmax static method) (ThompsonSampling static method) (UCB static method) sample_observation_space (BaseAgent property) (DDPG property) (DDQN property) (DQN property) (EGreedy property) (Evosax property) (Exp3 property) (ExpectedSarsa property) (NormalThompsonSampling property) (PPODiscrete property) (RandomScheduler property) (RoundRobinScheduler property) (Softmax property) (ThompsonSampling property) (UCB property)

save() (RLib method) set_agent() (RLib method) set_ext() (RLib method) set_loggers() (RLib method) setup_transformations() (BaseExt method) simple_resample() (in module reinforced_lib.utils.particle_filter) simple_transition() (in module reinforced_lib.utils.particle_filter) size (ReplayBuffer attribute) Softmax (class in reinforced_lib.agents.mab.softmax) SoftmaxState (class in reinforced_lib.agents.mab.softmax) source_to_name() (BaseLogger static method) states (ReplayBuffer attribute) StdoutLogger (class in reinforced_lib.logs.stdout_logger)

T

TensorboardLogger (class in reinforced_lib.logs.tb_logger) terminals (EvosaxState attribute) (ReplayBuffer attribute)

ThompsonSampling (class in reinforced_lib.agents.mab.thompson_sampling) ThompsonSamplingState (class in reinforced_lib.agents.mab.thompson_sampling) to_tflite() (RLib method) transform() (BaseExt method)

U

UCB (class in reinforced_lib.agents.mab.ucb) UCBState (class in reinforced_lib.agents.mab.ucb) UnimplementedSpaceError UnsupportedCustomLogsError UnsupportedLogTypeError update() (BaseAgent static method) (DDPG static method) (DDQN static method) (DQN static method) (EGreedy static method) (Evosax static method) (Exp3 static method) (ExpectedSarsa static method) (LogNormalThompsonSampling static method) (Masked static method) (NormalThompsonSampling static method) (ParticleFilter static method) (PPOContinuous static method) (PPODiscrete static method) (RandomScheduler static method) (RoundRobinScheduler static method) (Softmax static method) (ThompsonSampling static method) (UCB static method)

update_agent_state() (LogsObserver method) update_custom() (LogsObserver method) update_metrics() (LogsObserver method) update_observation_space (BaseAgent property) (DDPG property) (DDQN property) (DQN property) (EGreedy property) (Evosax property) (Exp3 property) (ExpectedSarsa property) (NormalThompsonSampling property) (PPOContinuous property) (PPODiscrete property) (RandomScheduler property) (RoundRobinScheduler property) (Softmax property) (ThompsonSampling property) (UCB property) update_observations() (LogsObserver method)

V

values() (AgentState method) (DDPGState method) (DDQNState method) (DQNState method) (EGreedyState method) (EvosaxState method) (Exp3State method) (ExpectedSarsaState method) (ExperienceReplay method) (MaskedState method) (NormalThompsonSamplingState method) (ParticleFilterState method) (PPOState method) (RandomSchedulerState method) (ReplayBuffer method) (RoundRobinSchedulerState method) (SoftmaxState method) (ThompsonSamplingState method) (UCBState method)

W

WeightsAndBiasesLogger (class in reinforced_lib.logs.wandb_logger)