Index

_

__call__() (arlbench.autorl.objectives.DiscountedReward static method), [1] (arlbench.autorl.objectives.DiscountedTrainReward static method), [1] (arlbench.autorl.objectives.Emissions static method), [1] (arlbench.autorl.objectives.Objective static method), [1] (arlbench.autorl.objectives.Reward static method), [1] (arlbench.autorl.objectives.Runtime static method), [1] (arlbench.autorl.objectives.TrainReward static method), [1] (arlbench.autorl.state_features.GradInfo static method), [1] (arlbench.autorl.state_features.LossInfo static method), [1] (arlbench.autorl.state_features.PredictionInfo static method), [1] (arlbench.autorl.state_features.StateFeature static method), [1] (arlbench.autorl.state_features.WeightInfo static method), [1] (arlbench.core.algorithms.dqn.models.CNNQ method), [1] (arlbench.core.algorithms.dqn.models.MLPQ method), [1] (arlbench.core.algorithms.ppo.models.CNNActorCritic method), [1] (arlbench.core.algorithms.ppo.models.MLPActorCritic method), [1] (arlbench.core.algorithms.sac.models.AlphaCoef method), [1] (arlbench.core.algorithms.sac.models.SACCNNActor method), [1] (arlbench.core.algorithms.sac.models.SACCNNCritic method), [1] (arlbench.core.algorithms.sac.models.SACMLPActor method), [1] (arlbench.core.algorithms.sac.models.SACMLPCritic method), [1] (arlbench.core.algorithms.sac.models.SACVectorCritic method), [1]

__lt__() (arlbench.autorl.objectives.Objective method), [1] __new__() (arlbench.autorl.objectives.Objective static method), [1] (arlbench.autorl.state_features.StateFeature static method), [1]

A

action (arlbench.core.algorithms.common.TimeStep attribute) (arlbench.core.algorithms.dqn.dqn.Transition attribute), [1] (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] (arlbench.core.algorithms.sac.sac.Transition attribute), [1] action_dim (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACCNNCritic attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) (arlbench.core.algorithms.sac.models.SACMLPCritic attribute) (arlbench.core.algorithms.sac.models.SACVectorCritic attribute) action_space (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1] (arlbench.core.environments.brax_env.BraxEnv property), [1] (arlbench.core.environments.BraxEnv property), [1] (arlbench.core.environments.envpool_env.EnvpoolEnv property), [1] (arlbench.core.environments.EnvpoolEnv property), [1] (arlbench.core.environments.gymnasium_env.GymnasiumEnv property), [1] (arlbench.core.environments.GymnasiumEnv property), [1] (arlbench.core.environments.gymnax_env.GymnaxEnv property), [1] (arlbench.core.environments.GymnaxEnv property), [1] (arlbench.core.environments.xland_env.XLandEnv property), [1] action_space() (arlbench.core.environments.autorl_env.Environment method), [1] (arlbench.core.environments.Environment method), [1] action_type (arlbench.core.algorithms.Algorithm property), [1] (arlbench.core.algorithms.algorithm.Algorithm property), [1] activation (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACCNNCritic attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) (arlbench.core.algorithms.sac.models.SACMLPCritic attribute) (arlbench.core.algorithms.sac.models.SACVectorCritic attribute) actor_grads (arlbench.core.algorithms.sac.sac.SACMetrics attribute), [1] (arlbench.core.algorithms.sac.SACMetrics attribute), [1] actor_loss (arlbench.core.algorithms.sac.sac.SACMetrics attribute), [1] (arlbench.core.algorithms.sac.SACMetrics attribute), [1] actor_train_state (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] advantages (arlbench.core.algorithms.ppo.ppo.PPOMetrics attribute), [1] (arlbench.core.algorithms.ppo.PPOMetrics attribute), [1] Algorithm (class in arlbench.core.algorithms), [1] (class in arlbench.core.algorithms.algorithm), [1] ALGORITHMS (arlbench.autorl.autorl_env.AutoRLEnv attribute) (arlbench.autorl.AutoRLEnv attribute) (arlbench.AutoRLEnv attribute) alpha_init (arlbench.core.algorithms.sac.models.AlphaCoef attribute) alpha_loss (arlbench.core.algorithms.sac.sac.SACMetrics attribute), [1] (arlbench.core.algorithms.sac.SACMetrics attribute), [1] alpha_train_state (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] AlphaCoef (class in arlbench.core.algorithms.sac.models), [1] arlbench module, [1] arlbench.arlbench module, [1] arlbench.autorl module, [1] arlbench.autorl.autorl_env module, [1] arlbench.autorl.checkpointing module, [1]

arlbench.autorl.objectives module, [1] arlbench.autorl.state_features module, [1] arlbench.core module, [1] arlbench.core.algorithms module, [1] arlbench.core.algorithms.algorithm module, [1] arlbench.core.algorithms.buffers module, [1] arlbench.core.algorithms.common module, [1] arlbench.core.algorithms.dqn module, [1] arlbench.core.algorithms.dqn.dqn module, [1] arlbench.core.algorithms.dqn.models module, [1] arlbench.core.algorithms.ppo module, [1] arlbench.core.algorithms.ppo.models module, [1] arlbench.core.algorithms.ppo.ppo module, [1] arlbench.core.algorithms.prioritised_item_buffer module, [1] arlbench.core.algorithms.sac module, [1] arlbench.core.algorithms.sac.models module, [1] arlbench.core.algorithms.sac.sac module, [1] arlbench.core.environments module, [1] arlbench.core.environments.autorl_env module, [1] arlbench.core.environments.brax_env module, [1] arlbench.core.environments.envpool_env module, [1] arlbench.core.environments.gymnasium_env module, [1] arlbench.core.environments.gymnax_env module, [1] arlbench.core.environments.make_env module arlbench.core.environments.xland_env module, [1] arlbench.core.running_statistics module, [1] arlbench.core.wrappers module, [1] arlbench.core.wrappers.flatten_observation module, [1] arlbench.core.wrappers.wrapper module, [1] arlbench.utils module, [1] arlbench.utils.common module, [1] Array (class in arlbench.core.running_statistics), [1] AutoML AutoRL AutoRLEnv (class in arlbench), [1] (class in arlbench.autorl), [1] (class in arlbench.autorl.autorl_env), [1]

B

BO BraxEnv (class in arlbench.core.environments), [1] (class in arlbench.core.environments.brax_env), [1] buffer_state (arlbench.core.algorithms.dqn.dqn.DQNState attribute), [1] (arlbench.core.algorithms.dqn.DQNState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOState attribute), [1] (arlbench.core.algorithms.ppo.PPOState attribute), [1] (arlbench.core.algorithms.sac.sac.SACState attribute), [1] (arlbench.core.algorithms.sac.SACState attribute), [1]

C

Checkpointer (class in arlbench.autorl.checkpointing), [1] checkpoints (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1] CNNActorCritic (class in arlbench.core.algorithms.ppo.models), [1] CNNQ (class in arlbench.core.algorithms.dqn.models), [1] config (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1] config_space (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1] config_space_to_gymnasium_space() (in module arlbench.utils), [1] (in module arlbench.utils.common), [1]

config_space_to_yaml() (in module arlbench.utils), [1] (in module arlbench.utils.common), [1] count (arlbench.core.running_statistics.RunningStatisticsState attribute) create_prioritised_item_buffer() (in module arlbench.core.algorithms.prioritised_item_buffer), [1] create_with_opt_state() (arlbench.core.algorithms.dqn.dqn.DQNTrainState class method), [1] (arlbench.core.algorithms.ppo.ppo.PPOTrainState class method), [1] (arlbench.core.algorithms.sac.sac.SACTrainState class method), [1] critic (arlbench.core.algorithms.sac.models.SACVectorCritic attribute) critic_grads (arlbench.core.algorithms.sac.sac.SACMetrics attribute), [1] (arlbench.core.algorithms.sac.SACMetrics attribute), [1] critic_loss (arlbench.core.algorithms.sac.sac.SACMetrics attribute), [1] (arlbench.core.algorithms.sac.SACMetrics attribute), [1] critic_train_state (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1]

D

denormalize() (in module arlbench.core.running_statistics), [1] discount_rewards() (in module arlbench.autorl.objectives), [1] DiscountedReward (class in arlbench.autorl.objectives), [1] DiscountedTrainReward (class in arlbench.autorl.objectives), [1] discrete (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) done (arlbench.core.algorithms.common.TimeStep attribute) (arlbench.core.algorithms.dqn.dqn.Transition attribute), [1] (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] (arlbench.core.algorithms.sac.sac.Transition attribute), [1] DQN (class in arlbench.core.algorithms), [1] (class in arlbench.core.algorithms.dqn), [1] (class in arlbench.core.algorithms.dqn.dqn), [1]

DQNMetrics (class in arlbench.core.algorithms.dqn), [1] (class in arlbench.core.algorithms.dqn.dqn), [1] DQNRunnerState (class in arlbench.core.algorithms.dqn), [1] (class in arlbench.core.algorithms.dqn.dqn), [1] DQNState (class in arlbench.core.algorithms.dqn), [1] (class in arlbench.core.algorithms.dqn.dqn), [1] DQNTrainingResult (class in arlbench.core.algorithms.dqn), [1] (class in arlbench.core.algorithms.dqn.dqn), [1] DQNTrainReturnT (in module arlbench.core.algorithms.dqn), [1] DQNTrainState (class in arlbench.core.algorithms.dqn.dqn), [1] dtype (arlbench.core.running_statistics.Array attribute)

E

Emissions (class in arlbench.autorl.objectives), [1] env_name (arlbench.core.environments.autorl_env.Environment property), [1] (arlbench.core.environments.Environment property), [1] env_state (arlbench.core.algorithms.dqn.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] Environment (class in arlbench.core.environments), [1] (class in arlbench.core.environments.autorl_env), [1] EnvpoolEnv (class in arlbench.core.environments), [1] (class in arlbench.core.environments.envpool_env), [1]

eval() (arlbench.autorl.autorl_env.AutoRLEnv method), [1] (arlbench.autorl.AutoRLEnv method), [1] (arlbench.AutoRLEnv method), [1] (arlbench.core.algorithms.Algorithm method), [1] (arlbench.core.algorithms.algorithm.Algorithm method), [1] eval_rewards (arlbench.core.algorithms.dqn.dqn.DQNTrainingResult attribute), [1] (arlbench.core.algorithms.dqn.DQNTrainingResult attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOTrainingResult attribute), [1] (arlbench.core.algorithms.ppo.PPOTrainingResult attribute), [1] (arlbench.core.algorithms.sac.sac.SACTrainingResult attribute), [1] (arlbench.core.algorithms.sac.SACTrainingResult attribute), [1]

F

FlattenObservationWrapper (class in arlbench.core.wrappers), [1] (class in arlbench.core.wrappers.flatten_observation), [1]

from_tuple() (arlbench.core.algorithms.common.TimeStep method)

G

get_algorithm_init_kwargs() (arlbench.autorl.autorl_env.AutoRLEnv method), [1] (arlbench.autorl.AutoRLEnv method), [1] (arlbench.AutoRLEnv method), [1] get_checkpoint_factory() (arlbench.core.algorithms.Algorithm static method), [1] (arlbench.core.algorithms.algorithm.Algorithm static method), [1] (arlbench.core.algorithms.DQN static method), [1] (arlbench.core.algorithms.dqn.DQN static method), [1] (arlbench.core.algorithms.dqn.dqn.DQN static method), [1] (arlbench.core.algorithms.PPO static method), [1] (arlbench.core.algorithms.ppo.PPO static method), [1] (arlbench.core.algorithms.ppo.ppo.PPO static method), [1] (arlbench.core.algorithms.SAC static method), [1] (arlbench.core.algorithms.sac.SAC static method), [1] (arlbench.core.algorithms.sac.sac.SAC static method), [1] get_default_hpo_config() (arlbench.core.algorithms.Algorithm static method), [1] (arlbench.core.algorithms.algorithm.Algorithm static method), [1] (arlbench.core.algorithms.DQN static method), [1] (arlbench.core.algorithms.dqn.DQN static method), [1] (arlbench.core.algorithms.dqn.dqn.DQN static method), [1] (arlbench.core.algorithms.PPO static method), [1] (arlbench.core.algorithms.ppo.PPO static method), [1] (arlbench.core.algorithms.ppo.ppo.PPO static method), [1] (arlbench.core.algorithms.SAC static method), [1] (arlbench.core.algorithms.sac.SAC static method), [1] (arlbench.core.algorithms.sac.sac.SAC static method), [1] get_default_nas_config() (arlbench.core.algorithms.Algorithm static method), [1] (arlbench.core.algorithms.algorithm.Algorithm static method), [1] (arlbench.core.algorithms.DQN static method), [1] (arlbench.core.algorithms.dqn.DQN static method), [1] (arlbench.core.algorithms.dqn.dqn.DQN static method), [1] (arlbench.core.algorithms.PPO static method), [1] (arlbench.core.algorithms.ppo.PPO static method), [1] (arlbench.core.algorithms.ppo.ppo.PPO static method), [1] (arlbench.core.algorithms.SAC static method), [1] (arlbench.core.algorithms.sac.SAC static method), [1] (arlbench.core.algorithms.sac.sac.SAC static method), [1] get_hpo_config_space() (arlbench.core.algorithms.Algorithm static method), [1] (arlbench.core.algorithms.algorithm.Algorithm static method), [1] (arlbench.core.algorithms.DQN static method), [1] (arlbench.core.algorithms.dqn.DQN static method), [1] (arlbench.core.algorithms.dqn.dqn.DQN static method), [1] (arlbench.core.algorithms.PPO static method), [1] (arlbench.core.algorithms.ppo.PPO static method), [1] (arlbench.core.algorithms.ppo.ppo.PPO static method), [1] (arlbench.core.algorithms.SAC static method), [1] (arlbench.core.algorithms.sac.SAC static method), [1] (arlbench.core.algorithms.sac.sac.SAC static method), [1]

get_nas_config_space() (arlbench.core.algorithms.Algorithm static method), [1] (arlbench.core.algorithms.algorithm.Algorithm static method), [1] (arlbench.core.algorithms.DQN static method), [1] (arlbench.core.algorithms.dqn.DQN static method), [1] (arlbench.core.algorithms.dqn.dqn.DQN static method), [1] (arlbench.core.algorithms.PPO static method), [1] (arlbench.core.algorithms.ppo.PPO static method), [1] (arlbench.core.algorithms.ppo.ppo.PPO static method), [1] (arlbench.core.algorithms.SAC static method), [1] (arlbench.core.algorithms.sac.SAC static method), [1] (arlbench.core.algorithms.sac.sac.SAC static method), [1] get_spec() (arlbench.autorl.objectives.DiscountedReward static method), [1] (arlbench.autorl.objectives.DiscountedTrainReward static method), [1] (arlbench.autorl.objectives.Emissions static method), [1] (arlbench.autorl.objectives.Objective static method), [1] (arlbench.autorl.objectives.Reward static method), [1] (arlbench.autorl.objectives.Runtime static method), [1] (arlbench.autorl.objectives.TrainReward static method), [1] get_state_space() (arlbench.autorl.state_features.GradInfo static method), [1] (arlbench.autorl.state_features.LossInfo static method), [1] (arlbench.autorl.state_features.PredictionInfo static method), [1] (arlbench.autorl.state_features.StateFeature static method), [1] (arlbench.autorl.state_features.WeightInfo static method), [1] global_step (arlbench.core.algorithms.dqn.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] GradInfo (class in arlbench.autorl.state_features), [1] grads (arlbench.core.algorithms.dqn.dqn.DQNMetrics attribute), [1] (arlbench.core.algorithms.dqn.DQNMetrics attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOMetrics attribute), [1] (arlbench.core.algorithms.ppo.PPOMetrics attribute), [1] gymnasium_space_to_gymnax_space() (in module arlbench.utils), [1] (in module arlbench.utils.common), [1] GymnasiumEnv (class in arlbench.core.environments), [1] (class in arlbench.core.environments.gymnasium_env), [1] GymnaxEnv (class in arlbench.core.environments), [1] (class in arlbench.core.environments.gymnax_env), [1]

H

hidden_size (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACCNNCritic attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) (arlbench.core.algorithms.sac.models.SACMLPCritic attribute) (arlbench.core.algorithms.sac.models.SACVectorCritic attribute)

HPO hpo_config (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1]

I

info (arlbench.core.algorithms.dqn.dqn.Transition attribute), [1] (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] (arlbench.core.algorithms.sac.sac.Transition attribute), [1] init() (arlbench.core.algorithms.Algorithm method), [1] (arlbench.core.algorithms.algorithm.Algorithm method), [1] (arlbench.core.algorithms.DQN method), [1] (arlbench.core.algorithms.dqn.DQN method), [1] (arlbench.core.algorithms.dqn.dqn.DQN method), [1] (arlbench.core.algorithms.PPO method), [1] (arlbench.core.algorithms.ppo.PPO method), [1] (arlbench.core.algorithms.ppo.ppo.PPO method), [1] (arlbench.core.algorithms.SAC method), [1] (arlbench.core.algorithms.sac.SAC method), [1] (arlbench.core.algorithms.sac.sac.SAC method), [1]

init_state() (in module arlbench.core.running_statistics), [1] items() (arlbench.core.algorithms.common.TimeStep method), [1]

K

KEY (arlbench.autorl.objectives.DiscountedReward attribute) (arlbench.autorl.objectives.DiscountedTrainReward attribute) (arlbench.autorl.objectives.Emissions attribute) (arlbench.autorl.objectives.Objective attribute) (arlbench.autorl.objectives.Reward attribute) (arlbench.autorl.objectives.Runtime attribute) (arlbench.autorl.objectives.TrainReward attribute) (arlbench.autorl.state_features.GradInfo attribute) (arlbench.autorl.state_features.LossInfo attribute) (arlbench.autorl.state_features.PredictionInfo attribute) (arlbench.autorl.state_features.StateFeature attribute) (arlbench.autorl.state_features.WeightInfo attribute)

keys() (arlbench.core.algorithms.common.TimeStep method), [1]

L

last_obs (arlbench.core.algorithms.common.TimeStep attribute) load() (arlbench.autorl.checkpointing.Checkpointer static method), [1] load_buffer() (arlbench.autorl.checkpointing.Checkpointer static method), [1] log_prob (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] log_std_max (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute)

log_std_min (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) loss (arlbench.core.algorithms.dqn.dqn.DQNMetrics attribute), [1] (arlbench.core.algorithms.dqn.DQNMetrics attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOMetrics attribute), [1] (arlbench.core.algorithms.ppo.PPOMetrics attribute), [1] LossInfo (class in arlbench.autorl.state_features), [1]

M

make_env() (in module arlbench.core.environments), [1], [2] (in module arlbench.core.environments.make_env) make_prioritised_item_buffer() (in module arlbench.core.algorithms.prioritised_item_buffer), [1] mean (arlbench.core.running_statistics.NestedMeanStd attribute) metrics (arlbench.core.algorithms.dqn.dqn.DQNTrainingResult attribute), [1] (arlbench.core.algorithms.dqn.DQNTrainingResult attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOTrainingResult attribute), [1] (arlbench.core.algorithms.ppo.PPOTrainingResult attribute), [1] (arlbench.core.algorithms.sac.sac.SACTrainingResult attribute), [1] (arlbench.core.algorithms.sac.SACTrainingResult attribute), [1] MLPActorCritic (class in arlbench.core.algorithms.ppo.models), [1] MLPQ (class in arlbench.core.algorithms.dqn.models), [1] mode() (arlbench.core.algorithms.sac.models.TanhTransformedDistribution method), [1] module arlbench, [1] arlbench.arlbench, [1] arlbench.autorl, [1] arlbench.autorl.autorl_env, [1] arlbench.autorl.checkpointing, [1] arlbench.autorl.objectives, [1] arlbench.autorl.state_features, [1] arlbench.core, [1] arlbench.core.algorithms, [1] arlbench.core.algorithms.algorithm, [1] arlbench.core.algorithms.buffers, [1] arlbench.core.algorithms.common, [1] arlbench.core.algorithms.dqn, [1] arlbench.core.algorithms.dqn.dqn, [1] arlbench.core.algorithms.dqn.models, [1] arlbench.core.algorithms.ppo, [1] arlbench.core.algorithms.ppo.models, [1] arlbench.core.algorithms.ppo.ppo, [1] arlbench.core.algorithms.prioritised_item_buffer, [1] arlbench.core.algorithms.sac, [1] arlbench.core.algorithms.sac.models, [1] arlbench.core.algorithms.sac.sac, [1] arlbench.core.environments, [1] arlbench.core.environments.autorl_env, [1] arlbench.core.environments.brax_env, [1] arlbench.core.environments.envpool_env, [1] arlbench.core.environments.gymnasium_env, [1] arlbench.core.environments.gymnax_env, [1] arlbench.core.environments.make_env arlbench.core.environments.xland_env, [1] arlbench.core.running_statistics, [1] arlbench.core.wrappers, [1] arlbench.core.wrappers.flatten_observation, [1] arlbench.core.wrappers.wrapper, [1] arlbench.utils, [1] arlbench.utils.common, [1]

MRP_FILE (arlbench.autorl.checkpointing.Checkpointer attribute) Multi-fidelity optimization

N

n_critics (arlbench.core.algorithms.sac.models.SACVectorCritic attribute) n_envs (arlbench.core.environments.autorl_env.Environment property), [1] (arlbench.core.environments.Environment property), [1] name (arlbench.core.algorithms.Algorithm attribute) (arlbench.core.algorithms.algorithm.Algorithm attribute) (arlbench.core.algorithms.DQN attribute) (arlbench.core.algorithms.dqn.DQN attribute) (arlbench.core.algorithms.dqn.dqn.DQN attribute) (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.PPO attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) (arlbench.core.algorithms.ppo.PPO attribute) (arlbench.core.algorithms.ppo.ppo.PPO attribute) (arlbench.core.algorithms.SAC attribute) (arlbench.core.algorithms.sac.models.AlphaCoef attribute) (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACCNNCritic attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) (arlbench.core.algorithms.sac.models.SACMLPCritic attribute) (arlbench.core.algorithms.sac.models.SACVectorCritic attribute) (arlbench.core.algorithms.sac.SAC attribute) (arlbench.core.algorithms.sac.sac.SAC attribute)

NestedMeanStd (class in arlbench.core.running_statistics), [1] network_state (arlbench.core.algorithms.sac.sac.SACTrainState attribute) NODES_FILE (arlbench.autorl.checkpointing.Checkpointer attribute) normalize() (in module arlbench.core.running_statistics), [1] normalizer_state (arlbench.core.algorithms.dqn.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] numpy_to_jax() (in module arlbench.core.environments.envpool_env), [1]

O

Objective (class in arlbench.autorl.objectives), [1] objectives (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1] obs (arlbench.core.algorithms.common.TimeStep attribute) (arlbench.core.algorithms.dqn.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.dqn.dqn.Transition attribute), [1] (arlbench.core.algorithms.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] (arlbench.core.algorithms.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.sac.Transition attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] observation_space (arlbench.autorl.autorl_env.AutoRLEnv property), [1] (arlbench.autorl.AutoRLEnv property), [1] (arlbench.AutoRLEnv property), [1] (arlbench.core.environments.brax_env.BraxEnv property), [1] (arlbench.core.environments.BraxEnv property), [1] (arlbench.core.environments.envpool_env.EnvpoolEnv property), [1] (arlbench.core.environments.EnvpoolEnv property), [1] (arlbench.core.environments.gymnasium_env.GymnasiumEnv property), [1] (arlbench.core.environments.GymnasiumEnv property), [1] (arlbench.core.environments.gymnax_env.GymnaxEnv property), [1] (arlbench.core.environments.GymnaxEnv property), [1] (arlbench.core.environments.xland_env.XLandEnv property), [1] (arlbench.core.wrappers.flatten_observation.FlattenObservationWrapper property), [1] (arlbench.core.wrappers.FlattenObservationWrapper property), [1]

observation_space() (arlbench.core.environments.autorl_env.Environment method), [1] (arlbench.core.environments.Environment method), [1] opt_state (arlbench.core.algorithms.dqn.dqn.DQNTrainState attribute) (arlbench.core.algorithms.ppo.ppo.PPOTrainState attribute)

P

parent (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) (arlbench.core.algorithms.sac.models.AlphaCoef attribute) (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACCNNCritic attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) (arlbench.core.algorithms.sac.models.SACMLPCritic attribute) (arlbench.core.algorithms.sac.models.SACVectorCritic attribute) PPO (class in arlbench.core.algorithms), [1] (class in arlbench.core.algorithms.ppo), [1] (class in arlbench.core.algorithms.ppo.ppo), [1] PPOMetrics (class in arlbench.core.algorithms.ppo), [1] (class in arlbench.core.algorithms.ppo.ppo), [1] PPORunnerState (class in arlbench.core.algorithms.ppo), [1] (class in arlbench.core.algorithms.ppo.ppo), [1]

PPOState (class in arlbench.core.algorithms.ppo), [1] (class in arlbench.core.algorithms.ppo.ppo), [1] PPOTrainingResult (class in arlbench.core.algorithms.ppo), [1] (class in arlbench.core.algorithms.ppo.ppo), [1] PPOTrainReturnT (in module arlbench.core.algorithms.ppo), [1] PPOTrainState (class in arlbench.core.algorithms.ppo.ppo), [1] predict() (arlbench.core.algorithms.Algorithm method), [1] (arlbench.core.algorithms.algorithm.Algorithm method), [1] (arlbench.core.algorithms.DQN method), [1] (arlbench.core.algorithms.dqn.DQN method), [1] (arlbench.core.algorithms.dqn.dqn.DQN method), [1] (arlbench.core.algorithms.PPO method), [1] (arlbench.core.algorithms.ppo.PPO method), [1] (arlbench.core.algorithms.ppo.ppo.PPO method), [1] (arlbench.core.algorithms.SAC method), [1] (arlbench.core.algorithms.sac.SAC method), [1] (arlbench.core.algorithms.sac.sac.SAC method), [1] PredictionInfo (class in arlbench.autorl.state_features), [1]

R

Random Search RANK (arlbench.autorl.objectives.DiscountedReward attribute) (arlbench.autorl.objectives.DiscountedTrainReward attribute) (arlbench.autorl.objectives.Emissions attribute) (arlbench.autorl.objectives.Objective attribute) (arlbench.autorl.objectives.Reward attribute) (arlbench.autorl.objectives.Runtime attribute) (arlbench.autorl.objectives.TrainReward attribute) recursive_concat() (in module arlbench.utils), [1] (in module arlbench.utils.common), [1] replace() (arlbench.core.algorithms.common.TimeStep method) (arlbench.core.algorithms.dqn.dqn.DQNTrainState method), [1] (arlbench.core.algorithms.ppo.ppo.PPOTrainState method), [1] (arlbench.core.algorithms.sac.sac.SACTrainState method), [1] (arlbench.core.running_statistics.NestedMeanStd method), [1] (arlbench.core.running_statistics.RunningStatisticsState method), [1] reset() (arlbench.autorl.autorl_env.AutoRLEnv method), [1] (arlbench.autorl.AutoRLEnv method), [1] (arlbench.AutoRLEnv method), [1] (arlbench.core.environments.autorl_env.Environment method), [1] (arlbench.core.environments.brax_env.BraxEnv method), [1] (arlbench.core.environments.BraxEnv method), [1] (arlbench.core.environments.Environment method), [1] (arlbench.core.environments.envpool_env.EnvpoolEnv method), [1] (arlbench.core.environments.EnvpoolEnv method), [1] (arlbench.core.environments.gymnasium_env.GymnasiumEnv method), [1] (arlbench.core.environments.GymnasiumEnv method), [1] (arlbench.core.environments.gymnax_env.GymnaxEnv method), [1] (arlbench.core.environments.GymnaxEnv method), [1] (arlbench.core.environments.xland_env.XLandEnv method), [1] (arlbench.core.wrappers.flatten_observation.FlattenObservationWrapper method), [1] (arlbench.core.wrappers.FlattenObservationWrapper method), [1]

reward (arlbench.core.algorithms.common.TimeStep attribute) (arlbench.core.algorithms.dqn.dqn.Transition attribute), [1] (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] (arlbench.core.algorithms.sac.sac.Transition attribute), [1] Reward (class in arlbench.autorl.objectives), [1] rng (arlbench.core.algorithms.dqn.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.sac.sac.SACRunnerState attribute), [1] (arlbench.core.algorithms.sac.SACRunnerState attribute), [1] run_arlbench() (in module arlbench), [1] (in module arlbench.arlbench), [1] runner_state (arlbench.core.algorithms.dqn.dqn.DQNState attribute), [1] (arlbench.core.algorithms.dqn.DQNState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOState attribute), [1] (arlbench.core.algorithms.ppo.PPOState attribute), [1] (arlbench.core.algorithms.sac.sac.SACState attribute), [1] (arlbench.core.algorithms.sac.SACState attribute), [1] RunningStatisticsState (class in arlbench.core.running_statistics), [1] Runtime (class in arlbench.autorl.objectives), [1]

S

SAC (class in arlbench.core.algorithms), [1] (class in arlbench.core.algorithms.sac), [1] (class in arlbench.core.algorithms.sac.sac), [1] SACCNNActor (class in arlbench.core.algorithms.sac.models), [1] SACCNNCritic (class in arlbench.core.algorithms.sac.models), [1] SACMetrics (class in arlbench.core.algorithms.sac), [1] (class in arlbench.core.algorithms.sac.sac), [1] SACMLPActor (class in arlbench.core.algorithms.sac.models), [1] SACMLPCritic (class in arlbench.core.algorithms.sac.models), [1] SACRunnerState (class in arlbench.core.algorithms.sac), [1] (class in arlbench.core.algorithms.sac.sac), [1] SACState (class in arlbench.core.algorithms.sac), [1] (class in arlbench.core.algorithms.sac.sac), [1] SACTrainingResult (class in arlbench.core.algorithms.sac), [1] (class in arlbench.core.algorithms.sac.sac), [1] SACTrainReturnT (in module arlbench.core.algorithms.sac), [1] SACTrainState (class in arlbench.core.algorithms.sac.sac), [1] SACVectorCritic (class in arlbench.core.algorithms.sac.models), [1] sample_action() (arlbench.core.environments.gymnax_env.GymnaxEnv method), [1] (arlbench.core.environments.GymnaxEnv method), [1] (arlbench.core.environments.xland_env.XLandEnv method), [1] sample_actions() (arlbench.core.environments.autorl_env.Environment method), [1] (arlbench.core.environments.Environment method), [1] save() (arlbench.autorl.checkpointing.Checkpointer static method), [1] save_buffer() (arlbench.autorl.checkpointing.Checkpointer static method), [1] save_defaults_to_yaml() (in module arlbench.utils), [1] (in module arlbench.utils.common), [1] SCALARS_FILE (arlbench.autorl.checkpointing.Checkpointer attribute) scope (arlbench.core.algorithms.dqn.models.CNNQ attribute) (arlbench.core.algorithms.dqn.models.MLPQ attribute) (arlbench.core.algorithms.ppo.models.CNNActorCritic attribute) (arlbench.core.algorithms.ppo.models.MLPActorCritic attribute) (arlbench.core.algorithms.sac.models.AlphaCoef attribute) (arlbench.core.algorithms.sac.models.SACCNNActor attribute) (arlbench.core.algorithms.sac.models.SACCNNCritic attribute) (arlbench.core.algorithms.sac.models.SACMLPActor attribute) (arlbench.core.algorithms.sac.models.SACMLPCritic attribute) (arlbench.core.algorithms.sac.models.SACVectorCritic attribute)

setup() (arlbench.core.algorithms.dqn.models.CNNQ method), [1] (arlbench.core.algorithms.dqn.models.MLPQ method), [1] (arlbench.core.algorithms.ppo.models.CNNActorCritic method), [1] (arlbench.core.algorithms.ppo.models.MLPActorCritic method), [1] (arlbench.core.algorithms.sac.models.AlphaCoef method), [1] (arlbench.core.algorithms.sac.models.SACCNNActor method), [1] (arlbench.core.algorithms.sac.models.SACCNNCritic method), [1] (arlbench.core.algorithms.sac.models.SACMLPActor method), [1] (arlbench.core.algorithms.sac.models.SACMLPCritic method), [1] shape (arlbench.core.running_statistics.Array attribute) StateFeature (class in arlbench.autorl.state_features), [1] std (arlbench.core.running_statistics.NestedMeanStd attribute) step() (arlbench.autorl.autorl_env.AutoRLEnv method), [1] (arlbench.autorl.AutoRLEnv method), [1] (arlbench.AutoRLEnv method), [1] (arlbench.core.environments.autorl_env.Environment method), [1] (arlbench.core.environments.brax_env.BraxEnv method), [1] (arlbench.core.environments.BraxEnv method), [1] (arlbench.core.environments.Environment method), [1] (arlbench.core.environments.envpool_env.EnvpoolEnv method), [1] (arlbench.core.environments.EnvpoolEnv method), [1] (arlbench.core.environments.gymnasium_env.GymnasiumEnv method), [1] (arlbench.core.environments.GymnasiumEnv method), [1] (arlbench.core.environments.gymnax_env.GymnaxEnv method), [1] (arlbench.core.environments.GymnaxEnv method), [1] (arlbench.core.environments.xland_env.XLandEnv method), [1] (arlbench.core.wrappers.flatten_observation.FlattenObservationWrapper method), [1] (arlbench.core.wrappers.FlattenObservationWrapper method), [1] summed_variance (arlbench.core.running_statistics.RunningStatisticsState attribute)

T

TanhTransformedDistribution (class in arlbench.core.algorithms.sac.models), [1] target_params (arlbench.core.algorithms.dqn.dqn.DQNTrainState attribute) (arlbench.core.algorithms.sac.sac.SACTrainState attribute) td_error (arlbench.core.algorithms.dqn.dqn.DQNMetrics attribute), [1] (arlbench.core.algorithms.dqn.DQNMetrics attribute), [1] (arlbench.core.algorithms.sac.sac.SACMetrics attribute), [1] (arlbench.core.algorithms.sac.SACMetrics attribute), [1] TimeStep (class in arlbench.core.algorithms.common), [1] to_tuple() (arlbench.core.algorithms.common.TimeStep method) train() (arlbench.core.algorithms.Algorithm method), [1] (arlbench.core.algorithms.algorithm.Algorithm method), [1] (arlbench.core.algorithms.DQN method), [1] (arlbench.core.algorithms.dqn.DQN method), [1] (arlbench.core.algorithms.dqn.dqn.DQN method), [1] (arlbench.core.algorithms.PPO method), [1] (arlbench.core.algorithms.ppo.PPO method), [1] (arlbench.core.algorithms.ppo.ppo.PPO method), [1] (arlbench.core.algorithms.SAC method), [1] (arlbench.core.algorithms.sac.SAC method), [1] (arlbench.core.algorithms.sac.sac.SAC method), [1]

train_state (arlbench.core.algorithms.dqn.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.dqn.DQNRunnerState attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPORunnerState attribute), [1] (arlbench.core.algorithms.ppo.PPORunnerState attribute), [1] TrainReward (class in arlbench.autorl.objectives), [1] trajectories (arlbench.core.algorithms.dqn.dqn.DQNTrainingResult attribute), [1] (arlbench.core.algorithms.dqn.DQNTrainingResult attribute), [1] (arlbench.core.algorithms.ppo.ppo.PPOTrainingResult attribute), [1] (arlbench.core.algorithms.ppo.PPOTrainingResult attribute), [1] (arlbench.core.algorithms.sac.sac.SACTrainingResult attribute), [1] (arlbench.core.algorithms.sac.SACTrainingResult attribute), [1] Transition (class in arlbench.core.algorithms.dqn.dqn), [1] (class in arlbench.core.algorithms.ppo.ppo), [1] (class in arlbench.core.algorithms.sac.sac), [1] tuple_concat() (in module arlbench.utils), [1] (in module arlbench.utils.common), [1]

U

uniform_sample() (in module arlbench.core.algorithms.buffers), [1] update() (arlbench.core.algorithms.DQN method), [1] (arlbench.core.algorithms.dqn.DQN method), [1] (arlbench.core.algorithms.dqn.dqn.DQN method), [1] (in module arlbench.core.running_statistics), [1] update_actor() (arlbench.core.algorithms.SAC method), [1] (arlbench.core.algorithms.sac.SAC method), [1] (arlbench.core.algorithms.sac.sac.SAC method), [1]

update_alpha() (arlbench.core.algorithms.SAC method), [1] (arlbench.core.algorithms.sac.SAC method), [1] (arlbench.core.algorithms.sac.sac.SAC method), [1] update_critic() (arlbench.core.algorithms.SAC method), [1] (arlbench.core.algorithms.sac.SAC method), [1] (arlbench.core.algorithms.sac.sac.SAC method), [1] update_hpo_config() (arlbench.core.algorithms.Algorithm method), [1] (arlbench.core.algorithms.algorithm.Algorithm method), [1]

V

value (arlbench.core.algorithms.ppo.ppo.Transition attribute), [1] (arlbench.core.algorithms.sac.sac.Transition attribute), [1]

values() (arlbench.core.algorithms.common.TimeStep method), [1]

W

WeightInfo (class in arlbench.autorl.state_features), [1]

Wrapper (class in arlbench.core.wrappers), [1] (class in arlbench.core.wrappers.wrapper), [1]

X

XLandEnv (class in arlbench.core.environments.xland_env), [1]