Index

_

__call__() (marl.exploration.eps_greedy.EpsGreedy method) (marl.exploration.expl_process.ExplorationProcess method) (marl.exploration.greedy.Greedy method) (marl.exploration.ou_noise.OUNoise method) (marl.model.qvalue.ActionProb method) (marl.model.qvalue.MultiQTable method) (marl.model.qvalue.QTable method) (marl.model.qvalue.VTable method) (marl.policy.policies.DeterministicPolicy method) (marl.policy.policies.QPolicy method) (marl.policy.policies.RandomPolicy method) (marl.policy.policies.StochasticPolicy method) (marl.policy.policy.Policy method)

A

action() (marl.agent.agent.Agent method) (marl.agent.agent.TrainableAgent method) (marl.marl.MARL method) (marl.marl.MAS method) action_space() (marl.agent.agent.TrainableAgent property) ActionProb (class in marl.model.qvalue) Agent (class in marl.agent.agent) agents (marl.agent.agent.Agent attribute)

append() (marl.marl.MAS method) available() (in module marl.agent.agent) (in module marl.experience.experience) (in module marl.exploration.expl_process) (in module marl.policy.policy) (marl.agent.agent.Agent class method) (marl.experience.experience.Experience class method) (marl.exploration.expl_process.ExplorationProcess class method) (marl.policy.policy.Policy class method)

B

beta_increment_per_sampling (marl.experience.replay_buffer.PrioritizedReplayMemory attribute)

C

capacity() (marl.experience.replay_buffer.PrioritizedReplayMemory property) ContinuousCritic (class in marl.model.nn.mlpnet)

ContinuousDQNAgent (class in marl.agent.q_agent) counter (marl.agent.agent.Agent attribute)

D

DDPGAgent (class in marl.agent.pg_agent) DeepACAgent (class in marl.agent.pg_agent)

delta() (marl.agent.pg_agent.PHCAgent property) DeterministicPolicy (class in marl.policy.policies) DQNAgent (class in marl.agent.q_agent)

E

EpsGreedy (class in marl.exploration.eps_greedy) Experience (class in marl.experience.experience)

experience (marl.experience.experience.Experience attribute) ExplorationProcess (class in marl.exploration.expl_process)

F

forward() (marl.model.nn.mlpnet.ContinuousCritic method) (marl.model.nn.mlpnet.GumbelMlpNet method) (marl.model.nn.mlpnet.MlpNet method) (marl.policy.policies.StochasticPolicy method)

G

get_by_id() (marl.marl.MAS method) get_by_name() (marl.marl.MAS method) get_transition() (marl.experience.replay_buffer.ReplayMemory method)

Greedy (class in marl.exploration.greedy) greedy_action() (marl.agent.agent.Agent method) (marl.marl.MARL method) GumbelMlpNet (class in marl.model.nn.mlpnet)

H

hidden_init() (in module marl.model.nn.mlpnet)

L

learn() (marl.agent.agent.TrainableAgent method) load() (marl.policy.policy.ModelBasedPolicy method)

load_model() (marl.marl.MARL method) lr_actor() (marl.agent.pg_agent.PGAgent property) lr_critic() (marl.agent.pg_agent.PGAgent property)

M

MAACAgent (class in marl.agent.maac_agent) MADDPGAgent (class in marl.agent.maac_agent) make() (in module marl.agent.agent) (in module marl.experience.experience) (in module marl.exploration.expl_process) (in module marl.policy.policy) (marl.agent.agent.Agent class method) (marl.experience.experience.Experience class method) (marl.exploration.expl_process.ExplorationProcess class method) (marl.policy.policy.Policy class method) MAPGAgent (class in marl.agent.maac_agent) MARL (class in marl.marl) marl.agent.agent (module) marl.agent.maac_agent (module) marl.agent.pg_agent (module) marl.agent.q_agent (module)

marl.experience.experience (module) marl.experience.replay_buffer (module) marl.exploration.eps_greedy (module) marl.exploration.expl_process (module) marl.exploration.greedy (module) marl.exploration.ou_noise (module) marl.marl (module) marl.model.nn.mlpnet (module) marl.model.qvalue (module) marl.policy.policies (module) marl.policy.policy (module) MAS (class in marl.marl) MATrainable (class in marl.agent.agent) MinimaxQAgent (class in marl.agent.q_agent) MlpNet (class in marl.model.nn.mlpnet) ModelBasedPolicy (class in marl.policy.policy) MultiQTable (class in marl.model.qvalue)

N

none_transition() (marl.experience.experience.Experience method)

O

observation_space() (marl.agent.agent.TrainableAgent property)

OUNoise (class in marl.exploration.ou_noise)

P

PGAgent (class in marl.agent.pg_agent) PHCAgent (class in marl.agent.pg_agent) Policy (class in marl.policy.policy) policy (marl.policy.policy.Policy attribute) PrioritizedReplayMemory (class in marl.experience.replay_buffer)

process (marl.exploration.expl_process.ExplorationProcess attribute) push() (marl.experience.experience.Experience method) (marl.experience.replay_buffer.PrioritizedReplayMemory method) (marl.experience.replay_buffer.ReplayMemory method) push_error() (marl.experience.replay_buffer.PrioritizedReplayMemory method) push_transition() (marl.experience.replay_buffer.PrioritizedReplayMemory method)

Q

Q() (marl.policy.policies.QPolicy property) q_table() (marl.model.qvalue.MultiQTable property) (marl.model.qvalue.QTable property)

QAgent (class in marl.agent.q_agent) QPolicy (class in marl.policy.policies) QTable (class in marl.model.qvalue) QTableAgent (class in marl.agent.q_agent)

R

RandomPolicy (class in marl.policy.policies) register() (in module marl.agent.agent) (in module marl.experience.experience) (in module marl.exploration.expl_process) (in module marl.policy.policy) (marl.agent.agent.Agent class method) (marl.experience.experience.Experience class method) (marl.exploration.expl_process.ExplorationProcess class method) (marl.policy.policy.Policy class method)

ReplayMemory (class in marl.experience.replay_buffer) reset() (marl.exploration.eps_greedy.EpsGreedy method) (marl.exploration.expl_process.ExplorationProcess method) (marl.exploration.ou_noise.OUNoise method) reset_exploration() (marl.agent.agent.TrainableAgent method) (marl.marl.MARL method) reset_parameters() (marl.model.nn.mlpnet.ContinuousCritic method) (marl.model.nn.mlpnet.MlpNet method)

S

sample() (marl.experience.experience.Experience method) (marl.experience.replay_buffer.PrioritizedReplayMemory method) (marl.experience.replay_buffer.ReplayMemory method) (marl.exploration.ou_noise.OUNoise method) sample_index() (marl.experience.replay_buffer.ReplayMemory method) save() (marl.policy.policy.ModelBasedPolicy method) save_all() (marl.agent.agent.TrainableAgent method) save_policy() (marl.agent.agent.TrainableAgent method) (marl.marl.MARL method)

set_mas() (marl.agent.agent.MATrainable method) shape() (marl.model.qvalue.ActionProb property) (marl.model.qvalue.MultiQTable property) (marl.model.qvalue.QTable property) (marl.model.qvalue.VTable property) soft_update() (marl.agent.maac_agent.MAPGAgent method) StochasticPolicy (class in marl.policy.policies) store_experience() (marl.agent.agent.TrainableAgent method) (marl.marl.MARL method)

T

target() (marl.agent.maac_agent.MAPGAgent method) (marl.agent.q_agent.ContinuousDQNAgent method) (marl.agent.q_agent.DQNAgent method) (marl.agent.q_agent.MinimaxQAgent method) (marl.agent.q_agent.QAgent method) (marl.agent.q_agent.QTableAgent method)

test() (marl.agent.agent.Agent method) TrainableAgent (class in marl.agent.agent)

U

update() (marl.experience.replay_buffer.PrioritizedReplayMemory method) (marl.exploration.eps_greedy.EpsGreedy method) (marl.exploration.expl_process.ExplorationProcess method) (marl.exploration.ou_noise.OUNoise method) update_actor() (marl.agent.maac_agent.MAACAgent method) (marl.agent.maac_agent.MADDPGAgent method) (marl.agent.pg_agent.DDPGAgent method) (marl.agent.pg_agent.DeepACAgent method) (marl.agent.pg_agent.PGAgent method) (marl.agent.pg_agent.PHCAgent method) update_critic() (marl.agent.maac_agent.MAPGAgent method) update_exploration() (marl.agent.agent.TrainableAgent method) (marl.marl.MARL method) update_model() (marl.agent.agent.TrainableAgent method) (marl.agent.maac_agent.MAPGAgent method) (marl.agent.pg_agent.PGAgent method) (marl.agent.q_agent.QAgent method) (marl.marl.MARL method)

update_q() (marl.agent.q_agent.DQNAgent method) (marl.agent.q_agent.MinimaxQAgent method) (marl.agent.q_agent.QAgent method) (marl.agent.q_agent.QTableAgent method) update_target_model() (marl.agent.q_agent.DQNAgent method) (marl.agent.q_agent.MinimaxQAgent method) (marl.agent.q_agent.QAgent method) (marl.agent.q_agent.QTableAgent method) update_target_policy() (marl.agent.pg_agent.DDPGAgent method) (marl.agent.pg_agent.DeepACAgent method) (marl.agent.pg_agent.PGAgent method) (marl.agent.pg_agent.PHCAgent method)

V

value() (marl.agent.q_agent.ContinuousDQNAgent method) (marl.agent.q_agent.DQNAgent method) (marl.agent.q_agent.MinimaxQAgent method) (marl.agent.q_agent.QAgent method) (marl.agent.q_agent.QTableAgent method)

VTable (class in marl.model.qvalue)