MALib
latest
Tutorials
Introduction
Quick Start
Key Concepts
Distributed Strategies
Environments
Clustered Deployment
API Documentation
malib.agent package
malib.backend package
malib.common package
malib.models package
malib.remote package
malib.rl package
malib.rollout package
malib.scenarios package
malib.utils package
Development
Contributing to MALib
Changelog
License
MALib
Index
Edit on GitHub
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
K
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
|
U
|
V
|
W
A
A2CPolicy (class in malib.rl.a2c.policy)
A2CTrainer (class in malib.rl.a2c.trainer)
ACC_REWARD (malib.utils.episode.Episode attribute)
ACTION (malib.utils.episode.Episode attribute)
action_adapter() (malib.rollout.envs.env.Environment static method)
ACTION_DIST (malib.utils.episode.Episode attribute)
ACTION_LOGITS (malib.utils.episode.Episode attribute)
ACTION_MASK (malib.utils.episode.Episode attribute)
action_mask_extract() (malib.rollout.envs.env.GroupWrapper method)
action_probabilities() (malib.utils.exploitability.NFSPPolicies method)
(malib.utils.exploitability.OSPolicyWrapper method)
action_spaces (malib.rollout.envs.env.Environment property)
(malib.rollout.envs.env.GroupWrapper property)
(malib.rollout.envs.env.Wrapper property)
(malib.rollout.envs.gym.env.GymEnv property)
(malib.rollout.envs.mdp.env.MDPEnvironment property)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv property)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv property)
actions_from_params() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
ActionSpace() (in module malib.rollout.envs.open_spiel.env)
Actor (class in malib.models.torch.continuous)
(class in malib.models.torch.discrete)
actor (malib.rl.common.policy.Policy property)
ActorCritic (class in malib.models.torch.net)
ActorProb (class in malib.models.torch.continuous)
add_batch() (malib.utils.replay_buffer.MultiagentReplayBuffer method)
(malib.utils.replay_buffer.ReplayBuffer method)
add_policies() (malib.agent.agent_interface.AgentInterface method)
(malib.agent.manager.TrainingManager method)
add_time() (malib.utils.timing.Timing method)
ADVANTAGE (malib.utils.episode.Episode attribute)
AGENT_EXPERIENCE_TABLE_NAME_GEN() (in module malib.utils.notations)
agent_groups (malib.agent.manager.TrainingManager property)
(malib.rollout.envs.env.GroupWrapper property)
agent_to_group() (malib.rollout.envs.env.GroupWrapper method)
AgentInterface (class in malib.agent.agent_interface)
apply_gradients() (malib.backend.parameter_server.ParameterServer method)
(malib.backend.parameter_server.Table method)
as_remote() (malib.remote.interface.RemoteInterface class method)
AsyncAgent (class in malib.agent.async_agent)
atanh() (malib.common.distributions.TanhBijector static method)
AttrDict (class in malib.utils.timing)
AvgTime (class in malib.utils.timing)
B
Batch (class in malib.utils.tianshou_batch)
BColors (class in malib.utils.typing)
BehaviorMode (class in malib.utils.typing)
BernoulliDistribution (class in malib.common.distributions)
BOLD (malib.utils.typing.BColors attribute)
BoxFlattenPreprocessor (class in malib.utils.preprocessor)
BoxStackedPreprocessor (class in malib.utils.preprocessor)
BufferDict (class in malib.utils.general)
build_state_from_observation() (malib.rollout.envs.env.GroupWrapper method)
build_state_spaces() (malib.rollout.envs.env.GroupWrapper method)
C
cancel_pending_tasks() (malib.common.manager.Manager method)
capacity (malib.utils.general.BufferDict property)
cat() (malib.utils.tianshou_batch.Batch static method)
cat_() (malib.utils.tianshou_batch.Batch method)
CategoricalDistribution (class in malib.common.distributions)
ClientHandler (class in malib.rollout.inference.ray.server)
close() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.Wrapper method)
(malib.rollout.envs.gym.env.GymEnv method)
(malib.rollout.envs.mdp.env.MDPEnvironment method)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv method)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv method)
collect_info() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.Wrapper method)
COMADiscreteCritic (class in malib.rl.coma.critic)
COMATrainer (class in malib.rl.coma.trainer)
compute_act_probs() (in module malib.utils.exploitability)
compute_action() (malib.rl.common.policy.Policy method)
(malib.rl.dqn.policy.DQNPolicy method)
(malib.rl.pg.policy.PGPolicy method)
(malib.rollout.inference.ray.server.RayInferenceWorkerSet method)
compute_episodic_return() (malib.utils.data.Postprocessor static method)
connect() (malib.agent.agent_interface.AgentInterface method)
ConstantSchedule (class in malib.utils.schedules)
convert_to_os_policies() (in module malib.utils.exploitability)
coordinate() (malib.rl.common.policy.Policy method)
copy() (malib.rl.common.policy.Policy class method)
(malib.scenarios.scenario.Scenario method)
CosineEmbeddingNetwork (class in malib.models.torch.discrete)
counter (malib.rl.common.trainer.Trainer property)
create_joint_action() (malib.rl.coma.trainer.COMATrainer method)
create_table() (malib.backend.parameter_server.ParameterServer method)
Critic (class in malib.models.torch.continuous)
(class in malib.models.torch.discrete)
critic (malib.rl.common.policy.Policy property)
CUR_OBS (malib.utils.episode.Episode attribute)
CUR_STATE (malib.utils.episode.Episode attribute)
custom_config (malib.rl.common.policy.Policy property)
D
data (malib.utils.typing.DataFrame attribute)
DataFrame (class in malib.utils.typing)
DataParallelNet (class in malib.models.torch.net)
decode() (malib.models.torch.continuous.VAE method)
deep_update() (in module malib.utils.general)
deprecated() (in module malib.utils.notations)
deregister_state() (malib.rl.common.policy.Policy method)
device (malib.agent.agent_interface.AgentInterface property)
(malib.rl.common.policy.Policy property)
DiagGaussianDistribution (class in malib.common.distributions)
DictFlattenPreprocessor (class in malib.utils.preprocessor)
DiscreteFlattenPreprocessor (class in malib.utils.preprocessor)
Distribution (class in malib.common.distributions)
DONE (malib.utils.episode.Episode attribute)
DQNPolicy (class in malib.rl.dqn.policy)
DQNTrainer (class in malib.rl.dqn.trainer)
E
empty() (malib.utils.tianshou_batch.Batch static method)
empty_() (malib.utils.tianshou_batch.Batch method)
end_consumer_pipe() (malib.backend.offline_dataset_server.OfflineDataset method)
end_producer_pipe() (malib.backend.offline_dataset_server.OfflineDataset method)
ENDC (malib.utils.typing.BColors attribute)
entropy (malib.common.distributions.MaskedCategorical property)
entropy() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.SquashedDiagGaussianDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
env_desc_gen() (in module malib.rollout.envs.gym)
(in module malib.rollout.envs.mdp)
(in module malib.rollout.envs.open_spiel)
(in module malib.rollout.envs.pettingzoo)
env_done_check() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.GroupWrapper method)
Environment (class in malib.rollout.envs.env)
Episode (class in malib.utils.episode)
EPISODE_EXPERIENCE_TABLE_NAME_GEN() (in module malib.utils.notations)
eps (malib.rl.dqn.policy.DQNPolicy property)
EXPLOITATION (malib.utils.typing.BehaviorMode attribute)
EXPLORATION (malib.utils.typing.BehaviorMode attribute)
F
f() (malib.models.torch.discrete.NoisyLinear method)
FAIL (malib.utils.typing.BColors attribute)
FLATTEN (malib.utils.preprocessor.Mode attribute)
flatten_dict() (in module malib.utils.general)
force_stop() (malib.common.manager.Manager method)
forward() (malib.common.distributions.TanhBijector static method)
(malib.models.torch.continuous.Actor method)
(malib.models.torch.continuous.ActorProb method)
(malib.models.torch.continuous.Critic method)
(malib.models.torch.continuous.Perturbation method)
(malib.models.torch.continuous.RecurrentActorProb method)
(malib.models.torch.continuous.RecurrentCritic method)
(malib.models.torch.continuous.VAE method)
(malib.models.torch.discrete.Actor method)
(malib.models.torch.discrete.CosineEmbeddingNetwork method)
(malib.models.torch.discrete.Critic method)
(malib.models.torch.discrete.FractionProposalNetwork method)
(malib.models.torch.discrete.ImplicitQuantileNetwork method)
(malib.models.torch.discrete.IntrinsicCuriosityModule method)
(malib.models.torch.discrete.NoisyLinear method)
(malib.models.torch.net.DataParallelNet method)
(malib.models.torch.net.MLP method)
(malib.models.torch.net.Net method)
(malib.models.torch.net.Recurrent method)
(malib.rl.coma.critic.COMADiscreteCritic method)
FractionProposalNetwork (class in malib.models.torch.discrete)
frozen_data() (in module malib.utils.general)
G
gae_return() (malib.utils.data.Postprocessor static method)
gen_policy() (malib.common.strategy_spec.StrategySpec method)
get_actions() (malib.common.distributions.Distribution method)
get_algorithm() (malib.agent.agent_interface.AgentInterface method)
get_algorthms() (malib.agent.agent_interface.AgentInterface method)
get_exp() (malib.agent.manager.TrainingManager method)
get_initial_state() (malib.rl.common.policy.Policy method)
get_interface_state() (malib.agent.agent_interface.AgentInterface method)
get_meta_data() (malib.common.strategy_spec.StrategySpec method)
get_noise() (malib.common.distributions.StateDependentNoiseDistribution method)
get_preprocessor() (in module malib.utils.preprocessor)
get_std() (malib.common.distributions.StateDependentNoiseDistribution method)
get_stopper() (in module malib.utils.stopping_conditions)
get_weights() (malib.backend.parameter_server.ParameterServer method)
(malib.backend.parameter_server.Table method)
governed_agents (malib.agent.agent_interface.AgentInterface property)
GroupWrapper (class in malib.rollout.envs.env)
gumbel_softmax() (in module malib.rl.common.misc)
GymEnv (class in malib.rollout.envs.gym.env)
H
HEADER (malib.utils.typing.BColors attribute)
I
identifier (malib.utils.typing.DataFrame attribute)
ImplicitQuantileNetwork (class in malib.models.torch.discrete)
IndependentAgent (class in malib.agent.indepdent_agent)
index() (malib.utils.general.BufferDict method)
index_func() (malib.utils.general.BufferDict method)
INFO (malib.utils.episode.Episode attribute)
IntrinsicCuriosityModule (class in malib.models.torch.discrete)
inverse() (malib.common.distributions.TanhBijector static method)
is_empty() (malib.utils.tianshou_batch.Batch method)
is_running() (malib.common.manager.Manager method)
(malib.remote.interface.RemoteInterface method)
iter_dicts_recursively() (in module malib.utils.general)
iter_many_dicts_recursively() (in module malib.utils.general)
iterate_recursively() (in module malib.utils.general)
K
kl_divergence() (in module malib.common.distributions)
L
LAST_REWARD (malib.utils.episode.Episode attribute)
linear_interpolation() (in module malib.utils.schedules)
LinearSchedule (class in malib.utils.schedules)
load() (malib.rl.common.policy.Policy method)
(malib.rl.dqn.policy.DQNPolicy method)
load_from_checkpoint() (malib.common.strategy_spec.StrategySpec method)
load_state_dict() (malib.rl.common.policy.Policy method)
(malib.rl.common.policy.SimpleObject method)
log_prob() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MaskedCategorical method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.SquashedDiagGaussianDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
log_prob_correction() (malib.common.distributions.TanhBijector method)
log_prob_from_params() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.SquashedDiagGaussianDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
logits (malib.common.distributions.MaskedCategorical property)
M
make_net() (in module malib.models.torch.net)
make_proba_distribution() (in module malib.common.distributions)
malib
module
malib.agent
module
malib.agent.agent_interface
module
malib.agent.async_agent
module
malib.agent.indepdent_agent
module
malib.agent.manager
module
malib.agent.team_agent
module
malib.backend
module
malib.backend.offline_dataset_server
module
malib.backend.parameter_server
module
malib.common
module
malib.common.distributions
module
malib.common.manager
module
malib.common.strategy_spec
module
malib.models
module
malib.models.torch
module
malib.models.torch.continuous
module
malib.models.torch.discrete
module
malib.models.torch.net
module
malib.registration
module
malib.remote
module
malib.remote.interface
module
malib.rl
module
malib.rl.a2c
module
malib.rl.a2c.config
module
malib.rl.a2c.policy
module
malib.rl.a2c.trainer
module
malib.rl.coma
module
malib.rl.coma.critic
module
malib.rl.coma.trainer
module
malib.rl.common
module
malib.rl.common.misc
module
malib.rl.common.policy
module
malib.rl.common.trainer
module
malib.rl.discrete_sac
module
malib.rl.discrete_sac.policy
module
malib.rl.discrete_sac.trainer
module
malib.rl.dqn
module
malib.rl.dqn.config
module
malib.rl.dqn.policy
module
malib.rl.dqn.trainer
module
malib.rl.maddpg
module
malib.rl.maddpg.loss
module
malib.rl.maddpg.trainer
module
malib.rl.mappo
module
malib.rl.mappo.config
module
malib.rl.mappo.policy
module
malib.rl.mappo.trainer
module
malib.rl.pg
module
malib.rl.pg.config
module
malib.rl.pg.policy
module
malib.rl.pg.trainer
module
malib.rl.ppo
module
malib.rl.ppo.policy
module
malib.rl.ppo.trainer
module
malib.rl.qmix
module
malib.rl.qmix.q_mixer
module
malib.rl.qmix.trainer
module
malib.rl.random
module
malib.rl.random.config
module
malib.rl.random.policy
module
malib.rl.random.random_trainer
module
malib.rl.sac
module
malib.rl.sac.policy
module
malib.rl.sac.trainer
module
malib.rollout.envs.env
module
malib.rollout.envs.gym
module
malib.rollout.envs.gym.env
module
malib.rollout.envs.mdp
module
malib.rollout.envs.mdp.env
module
malib.rollout.envs.open_spiel
module
malib.rollout.envs.open_spiel.env
module
malib.rollout.envs.pettingzoo
module
malib.rollout.envs.pettingzoo.env
module
malib.rollout.envs.pettingzoo.scenario_configs_ref
module
malib.rollout.inference
module
malib.rollout.inference.ray.server
module
malib.scenarios
module
malib.scenarios.scenario
module
malib.settings
module
malib.utils
module
malib.utils.data
module
malib.utils.episode
module
malib.utils.exploitability
module
malib.utils.general
module
malib.utils.logging
module
malib.utils.monitor
module
malib.utils.notations
module
malib.utils.preprocessor
module
malib.utils.replay_buffer
module
malib.utils.schedules
module
malib.utils.statistic
module
malib.utils.stopping_conditions
module
malib.utils.tianshou_batch
module
malib.utils.timing
module
malib.utils.typing
module
Manager (class in malib.common.manager)
masked_logits() (in module malib.rl.common.misc)
masked_softmax() (malib.common.distributions.MaskedCategorical static method)
MaskedCategorical (class in malib.common.distributions)
MaxIterationStopping (class in malib.utils.stopping_conditions)
MDPEnvironment (class in malib.rollout.envs.mdp.env)
measure_exploitability() (in module malib.utils.exploitability)
merge_dicts() (in module malib.utils.general)
MergeStopping (class in malib.utils.stopping_conditions)
meta_data (malib.utils.typing.DataFrame attribute)
miniblock() (in module malib.models.torch.net)
MLP (class in malib.models.torch.net)
Mode (class in malib.utils.preprocessor)
mode() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.SquashedDiagGaussianDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
model_config (malib.rl.common.policy.Policy property)
module
malib
malib.agent
malib.agent.agent_interface
malib.agent.async_agent
malib.agent.indepdent_agent
malib.agent.manager
malib.agent.team_agent
malib.backend
malib.backend.offline_dataset_server
malib.backend.parameter_server
malib.common
malib.common.distributions
malib.common.manager
malib.common.strategy_spec
malib.models
malib.models.torch
malib.models.torch.continuous
malib.models.torch.discrete
malib.models.torch.net
malib.registration
malib.remote
malib.remote.interface
malib.rl
malib.rl.a2c
malib.rl.a2c.config
malib.rl.a2c.policy
malib.rl.a2c.trainer
malib.rl.coma
malib.rl.coma.critic
malib.rl.coma.trainer
malib.rl.common
malib.rl.common.misc
malib.rl.common.policy
malib.rl.common.trainer
malib.rl.discrete_sac
malib.rl.discrete_sac.policy
malib.rl.discrete_sac.trainer
malib.rl.dqn
malib.rl.dqn.config
malib.rl.dqn.policy
malib.rl.dqn.trainer
malib.rl.maddpg
malib.rl.maddpg.loss
malib.rl.maddpg.trainer
malib.rl.mappo
malib.rl.mappo.config
malib.rl.mappo.policy
malib.rl.mappo.trainer
malib.rl.pg
malib.rl.pg.config
malib.rl.pg.policy
malib.rl.pg.trainer
malib.rl.ppo
malib.rl.ppo.policy
malib.rl.ppo.trainer
malib.rl.qmix
malib.rl.qmix.q_mixer
malib.rl.qmix.trainer
malib.rl.random
malib.rl.random.config
malib.rl.random.policy
malib.rl.random.random_trainer
malib.rl.sac
malib.rl.sac.policy
malib.rl.sac.trainer
malib.rollout.envs.env
malib.rollout.envs.gym
malib.rollout.envs.gym.env
malib.rollout.envs.mdp
malib.rollout.envs.mdp.env
malib.rollout.envs.open_spiel
malib.rollout.envs.open_spiel.env
malib.rollout.envs.pettingzoo
malib.rollout.envs.pettingzoo.env
malib.rollout.envs.pettingzoo.scenario_configs_ref
malib.rollout.inference
malib.rollout.inference.ray.server
malib.scenarios
malib.scenarios.scenario
malib.settings
malib.utils
malib.utils.data
malib.utils.episode
malib.utils.exploitability
malib.utils.general
malib.utils.logging
malib.utils.monitor
malib.utils.notations
malib.utils.preprocessor
malib.utils.replay_buffer
malib.utils.schedules
malib.utils.statistic
malib.utils.stopping_conditions
malib.utils.tianshou_batch
malib.utils.timing
malib.utils.typing
multiagent_post_process() (malib.agent.agent_interface.AgentInterface method)
(malib.agent.indepdent_agent.IndependentAgent method)
(malib.agent.team_agent.TeamAgent method)
MultiagentReplayBuffer (class in malib.utils.replay_buffer)
MultiCategoricalDistribution (class in malib.common.distributions)
N
Net (class in malib.models.torch.net)
NewEpisodeDict (class in malib.utils.episode)
NewEpisodeList (class in malib.utils.episode)
NEXT_ACTION_MASK (malib.utils.episode.Episode attribute)
NEXT_OBS (malib.utils.episode.Episode attribute)
NEXT_STATE (malib.utils.episode.Episode attribute)
NFSPPolicies (class in malib.utils.exploitability)
NoisyLinear (class in malib.models.torch.discrete)
norm() (malib.utils.statistic.RunningMeanStd method)
normalized_entropy (malib.common.distributions.MaskedCategorical property)
NoStoppingCondition (class in malib.utils.stopping_conditions)
num_policy (malib.common.strategy_spec.StrategySpec property)
O
observation_space (malib.utils.preprocessor.Preprocessor property)
observation_spaces (malib.rollout.envs.env.Environment property)
(malib.rollout.envs.env.GroupWrapper property)
(malib.rollout.envs.env.Wrapper property)
(malib.rollout.envs.gym.env.GymEnv property)
(malib.rollout.envs.mdp.env.MDPEnvironment property)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv property)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv property)
ObservationSpace() (in module malib.rollout.envs.open_spiel.env)
OfflineDataset (class in malib.backend.offline_dataset_server)
OKBLUE (malib.utils.typing.BColors attribute)
OKCYAN (malib.utils.typing.BColors attribute)
OKGREEN (malib.utils.typing.BColors attribute)
onehot_from_logits() (in module malib.rl.common.misc)
OpenSpielEnv (class in malib.rollout.envs.open_spiel.env)
original_space (malib.utils.preprocessor.Preprocessor property)
OSPolicyWrapper (class in malib.utils.exploitability)
P
parallel_simulate (malib.rollout.envs.pettingzoo.env.PettingZooEnv property)
parameters() (malib.rl.common.policy.Policy method)
(malib.rl.common.trainer.Trainer method)
(malib.rl.dqn.policy.DQNPolicy method)
ParameterServer (class in malib.backend.parameter_server)
Perturbation (class in malib.models.torch.continuous)
PettingZooEnv (class in malib.rollout.envs.pettingzoo.env)
PGPolicy (class in malib.rl.pg.policy)
PGTrainer (class in malib.rl.pg.trainer)
PiecewiseSchedule (class in malib.utils.schedules)
Policy (class in malib.rl.common.policy)
policy (malib.rl.common.trainer.Trainer property)
possible_agents (malib.rollout.envs.env.Environment property)
(malib.rollout.envs.env.GroupWrapper property)
(malib.rollout.envs.env.Wrapper property)
(malib.rollout.envs.gym.env.GymEnv property)
(malib.rollout.envs.mdp.env.MDPEnvironment property)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv property)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv property)
post_process() (malib.rl.a2c.trainer.A2CTrainer method)
(malib.rl.coma.trainer.COMATrainer method)
(malib.rl.common.trainer.Trainer method)
(malib.rl.dqn.trainer.DQNTrainer method)
(malib.rl.pg.trainer.PGTrainer method)
Postprocessor (class in malib.utils.data)
PowerSchedule (class in malib.utils.schedules)
PRE_DONE (malib.utils.episode.Episode attribute)
PRE_REWARD (malib.utils.episode.Episode attribute)
Preprocessor (class in malib.utils.preprocessor)
preprocessor (malib.rl.common.policy.Policy property)
prob() (malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
proba_distribution() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.SquashedDiagGaussianDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
proba_distribution_net() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
probs (malib.common.distributions.MaskedCategorical property)
pull() (malib.agent.agent_interface.AgentInterface method)
push() (malib.agent.agent_interface.AgentInterface method)
R
RandomPolicy (class in malib.rl.random.policy)
RandomTrainer (class in malib.rl.random.random_trainer)
RayInferenceWorkerSet (class in malib.rollout.inference.ray.server)
read_table() (in module malib.backend.offline_dataset_server)
record() (malib.utils.episode.Episode method)
(malib.utils.episode.NewEpisodeDict method)
(malib.utils.episode.NewEpisodeList method)
record_episode_info_step() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.GroupWrapper method)
Recurrent (class in malib.models.torch.net)
RecurrentActorProb (class in malib.models.torch.continuous)
RecurrentCritic (class in malib.models.torch.continuous)
recver (malib.rollout.inference.ray.server.ClientHandler property)
register_custom_algorithm() (malib.registration.Registry static method)
register_custom_env() (malib.registration.Registry static method)
register_custom_model() (malib.registration.Registry static method)
register_custom_policy() (malib.registration.Registry static method)
register_policy_id() (malib.common.strategy_spec.StrategySpec method)
register_state() (malib.rl.common.policy.Policy method)
registered_networks (malib.rl.common.policy.Policy property)
Registry (class in malib.registration)
RemoteInterface (class in malib.remote.interface)
render() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.Wrapper method)
(malib.rollout.envs.gym.env.GymEnv method)
(malib.rollout.envs.mdp.env.MDPEnvironment method)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv method)
ReplayBuffer (class in malib.utils.replay_buffer)
reset() (malib.agent.agent_interface.AgentInterface method)
(malib.models.torch.discrete.NoisyLinear method)
(malib.rl.common.policy.Policy method)
(malib.rl.common.trainer.Trainer method)
(malib.rl.dqn.policy.DQNPolicy method)
(malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.GroupWrapper method)
(malib.rollout.envs.env.Wrapper method)
(malib.rollout.envs.gym.env.GymEnv method)
(malib.rollout.envs.mdp.env.MDPEnvironment method)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv method)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv method)
retrive_results() (malib.agent.manager.TrainingManager method)
(malib.common.manager.Manager method)
REWARD (malib.utils.episode.Episode attribute)
RewardImprovementStopping (class in malib.utils.stopping_conditions)
RNN_STATE (malib.utils.episode.Episode attribute)
rnn_states (malib.rollout.inference.ray.server.ClientHandler property)
rsample() (malib.common.distributions.MaskedCategorical method)
run() (malib.agent.manager.TrainingManager method)
RunningMeanStd (class in malib.utils.statistic)
runtime_config (malib.rollout.inference.ray.server.ClientHandler property)
runtime_ids (malib.agent.manager.TrainingManager property)
S
sample() (malib.common.distributions.BernoulliDistribution method)
(malib.common.distributions.CategoricalDistribution method)
(malib.common.distributions.DiagGaussianDistribution method)
(malib.common.distributions.Distribution method)
(malib.common.distributions.MaskedCategorical method)
(malib.common.distributions.MultiCategoricalDistribution method)
(malib.common.distributions.SquashedDiagGaussianDistribution method)
(malib.common.distributions.StateDependentNoiseDistribution method)
(malib.common.strategy_spec.StrategySpec method)
(malib.models.torch.discrete.NoisyLinear method)
(malib.utils.replay_buffer.MultiagentReplayBuffer method)
(malib.utils.replay_buffer.ReplayBuffer method)
sample_gumbel() (in module malib.rl.common.misc)
sample_indices() (malib.utils.replay_buffer.ReplayBuffer method)
sample_noise() (in module malib.models.torch.discrete)
sample_weights() (malib.common.distributions.StateDependentNoiseDistribution method)
save() (malib.rl.common.policy.Policy method)
(malib.rl.dqn.policy.DQNPolicy method)
(malib.rollout.inference.ray.server.RayInferenceWorkerSet method)
Scenario (class in malib.scenarios.scenario)
Schedule (class in malib.utils.schedules)
seed() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.Wrapper method)
(malib.rollout.envs.mdp.env.MDPEnvironment method)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv method)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv method)
sender (malib.rollout.inference.ray.server.ClientHandler property)
set_data() (malib.utils.general.BufferDict method)
set_data_func() (malib.utils.general.BufferDict method)
set_running() (malib.remote.interface.RemoteInterface method)
set_weights() (malib.backend.parameter_server.ParameterServer method)
(malib.backend.parameter_server.Table method)
setup() (malib.rl.a2c.trainer.A2CTrainer method)
(malib.rl.coma.trainer.COMATrainer method)
(malib.rl.common.trainer.Trainer method)
(malib.rl.dqn.trainer.DQNTrainer method)
(malib.rl.pg.trainer.PGTrainer method)
shape (malib.utils.preprocessor.BoxFlattenPreprocessor property)
(malib.utils.preprocessor.BoxStackedPreprocessor property)
(malib.utils.preprocessor.DictFlattenPreprocessor property)
(malib.utils.preprocessor.DiscreteFlattenPreprocessor property)
(malib.utils.preprocessor.Preprocessor property)
(malib.utils.preprocessor.TupleFlattenPreprocessor property)
(malib.utils.tianshou_batch.Batch property)
should_stop() (malib.utils.stopping_conditions.MaxIterationStopping method)
(malib.utils.stopping_conditions.MergeStopping method)
(malib.utils.stopping_conditions.NoStoppingCondition method)
(malib.utils.stopping_conditions.RewardImprovementStopping method)
(malib.utils.stopping_conditions.StopImmediately method)
(malib.utils.stopping_conditions.StoppingCondition method)
shutdown() (malib.rollout.inference.ray.server.RayInferenceWorkerSet method)
SimpleObject (class in malib.rl.common.policy)
size (malib.utils.preprocessor.BoxFlattenPreprocessor property)
(malib.utils.preprocessor.BoxStackedPreprocessor property)
(malib.utils.preprocessor.DictFlattenPreprocessor property)
(malib.utils.preprocessor.DiscreteFlattenPreprocessor property)
(malib.utils.preprocessor.Preprocessor property)
(malib.utils.preprocessor.TupleFlattenPreprocessor property)
soft_update() (in module malib.rl.common.misc)
softmax() (in module malib.rl.common.misc)
split() (malib.utils.tianshou_batch.Batch method)
SquashedDiagGaussianDistribution (class in malib.common.distributions)
STACK (malib.utils.preprocessor.Mode attribute)
stack() (malib.utils.tianshou_batch.Batch static method)
stack_() (malib.utils.tianshou_batch.Batch method)
start() (malib.backend.offline_dataset_server.OfflineDataset method)
(malib.backend.parameter_server.ParameterServer method)
start_consumer_pipe() (malib.backend.offline_dataset_server.OfflineDataset method)
start_producer_pipe() (malib.backend.offline_dataset_server.OfflineDataset method)
STATE_ACTION_VALUE (malib.utils.episode.Episode attribute)
state_dict() (malib.rl.common.policy.Policy method)
(malib.rl.common.policy.SimpleObject method)
state_spaces (malib.rollout.envs.env.GroupWrapper property)
STATE_VALUE (malib.utils.episode.Episode attribute)
STATE_VALUE_TARGET (malib.utils.episode.Episode attribute)
StateDependentNoiseDistribution (class in malib.common.distributions)
step() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.Wrapper method)
step_counter() (malib.rl.common.trainer.Trainer method)
stop_pending_tasks() (malib.remote.interface.RemoteInterface method)
StopImmediately (class in malib.utils.stopping_conditions)
StoppingCondition (class in malib.utils.stopping_conditions)
StrategySpec (class in malib.common.strategy_spec)
sum_independent_dims() (in module malib.common.distributions)
sync_remote_parameters() (malib.agent.agent_interface.AgentInterface method)
T
Table (class in malib.backend.parameter_server)
TanhBijector (class in malib.common.distributions)
target_actor (malib.rl.common.policy.Policy property)
target_critic (malib.rl.common.policy.Policy property)
TeamAgent (class in malib.agent.team_agent)
tensor_cast() (in module malib.utils.general)
terminate() (malib.agent.manager.TrainingManager method)
(malib.common.manager.Manager method)
time_avg() (malib.utils.timing.Timing method)
time_step() (malib.rollout.envs.env.Environment method)
(malib.rollout.envs.env.GroupWrapper method)
(malib.rollout.envs.gym.env.GymEnv method)
(malib.rollout.envs.mdp.env.MDPEnvironment method)
(malib.rollout.envs.open_spiel.env.OpenSpielEnv method)
(malib.rollout.envs.pettingzoo.env.PettingZooEnv method)
timeit() (malib.utils.timing.Timing method)
Timing (class in malib.utils.timing)
TimingContext (class in malib.utils.timing)
to() (malib.rl.common.policy.Policy method)
to_numpy() (in module malib.utils.replay_buffer)
(malib.utils.episode.Episode method)
(malib.utils.episode.NewEpisodeDict method)
(malib.utils.episode.NewEpisodeList method)
(malib.utils.tianshou_batch.Batch method)
to_torch() (in module malib.utils.data)
(malib.utils.tianshou_batch.Batch method)
todict() (malib.utils.timing.Timing method)
tofloat() (malib.utils.timing.AvgTime method)
train() (malib.agent.agent_interface.AgentInterface method)
(malib.rl.a2c.trainer.A2CTrainer method)
(malib.rl.coma.trainer.COMATrainer method)
(malib.rl.common.trainer.Trainer method)
(malib.rl.dqn.trainer.DQNTrainer method)
(malib.rl.pg.trainer.PGTrainer method)
train_critic() (malib.rl.coma.trainer.COMATrainer method)
Trainer (class in malib.rl.common.trainer)
training (malib.models.torch.continuous.Actor attribute)
(malib.models.torch.continuous.ActorProb attribute)
(malib.models.torch.continuous.Critic attribute)
(malib.models.torch.continuous.Perturbation attribute)
(malib.models.torch.continuous.RecurrentActorProb attribute)
(malib.models.torch.continuous.RecurrentCritic attribute)
(malib.models.torch.continuous.VAE attribute)
(malib.models.torch.discrete.Actor attribute)
(malib.models.torch.discrete.CosineEmbeddingNetwork attribute)
(malib.models.torch.discrete.Critic attribute)
(malib.models.torch.discrete.FractionProposalNetwork attribute)
(malib.models.torch.discrete.ImplicitQuantileNetwork attribute)
(malib.models.torch.discrete.IntrinsicCuriosityModule attribute)
(malib.models.torch.discrete.NoisyLinear attribute)
(malib.models.torch.net.ActorCritic attribute)
(malib.models.torch.net.DataParallelNet attribute)
(malib.models.torch.net.MLP attribute)
(malib.models.torch.net.Net attribute)
(malib.models.torch.net.Recurrent attribute)
(malib.rl.coma.critic.COMADiscreteCritic attribute)
training_config (malib.rl.common.trainer.Trainer property)
TrainingManager (class in malib.agent.manager)
transform() (malib.utils.preprocessor.BoxFlattenPreprocessor method)
(malib.utils.preprocessor.BoxStackedPreprocessor method)
(malib.utils.preprocessor.DictFlattenPreprocessor method)
(malib.utils.preprocessor.DiscreteFlattenPreprocessor method)
(malib.utils.preprocessor.Preprocessor method)
(malib.utils.preprocessor.TupleFlattenPreprocessor method)
TupleFlattenPreprocessor (class in malib.utils.preprocessor)
U
UNDERLINE (malib.utils.typing.BColors attribute)
unflatten_dict() (in module malib.utils.general)
unflatten_list_dict() (in module malib.utils.general)
unflattened_lookup() (in module malib.utils.general)
update() (malib.utils.statistic.RunningMeanStd method)
(malib.utils.tianshou_batch.Batch method)
update_configs() (in module malib.utils.general)
update_dataset_config() (in module malib.utils.general)
update_evaluation_config() (in module malib.utils.general)
update_global_evaluator_config() (in module malib.utils.general)
update_parameter_server_config() (in module malib.utils.general)
update_parameters() (malib.rl.common.policy.Policy method)
update_prob_list() (malib.common.strategy_spec.StrategySpec method)
update_rollout_configs() (in module malib.utils.general)
update_training_config() (in module malib.utils.general)
V
VAE (class in malib.models.torch.continuous)
validate_meta_data() (in module malib.common.strategy_spec)
value() (malib.utils.schedules.ConstantSchedule method)
(malib.utils.schedules.LinearSchedule method)
(malib.utils.schedules.PiecewiseSchedule method)
(malib.utils.schedules.PowerSchedule method)
(malib.utils.schedules.Schedule method)
value_function() (malib.rl.a2c.policy.A2CPolicy method)
(malib.rl.dqn.policy.DQNPolicy method)
(malib.rl.pg.policy.PGPolicy method)
W
wait() (malib.common.manager.Manager method)
WARNING (malib.utils.typing.BColors attribute)
with_updates() (malib.scenarios.scenario.Scenario method)
workers (malib.agent.manager.TrainingManager property)
(malib.common.manager.Manager property)
Wrapper (class in malib.rollout.envs.env)
write() (malib.utils.preprocessor.BoxFlattenPreprocessor method)
(malib.utils.preprocessor.BoxStackedPreprocessor method)
(malib.utils.preprocessor.DictFlattenPreprocessor method)
(malib.utils.preprocessor.DiscreteFlattenPreprocessor method)
(malib.utils.preprocessor.Preprocessor method)
(malib.utils.preprocessor.TupleFlattenPreprocessor method)
write_table() (in module malib.backend.offline_dataset_server)
write_to_tensorboard() (in module malib.utils.monitor)
Read the Docs
v: latest
Versions
latest
stable
documentation
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds