Index

_

__eq__() (aitraineree.buffers.per.PERBuffer method) (aitraineree.buffers.replay.ReplayBuffer method) (aitraineree.buffers.rollout.RolloutBuffer method) __hash__ (aitraineree.buffers.per.PERBuffer attribute) (aitraineree.buffers.replay.ReplayBuffer attribute) (aitraineree.buffers.rollout.RolloutBuffer attribute) __init__() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.buffers.per.PERBuffer method) (aitraineree.buffers.replay.ReplayBuffer method) (aitraineree.buffers.rollout.RolloutBuffer method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.networks.bodies.ConvNet method) (aitraineree.networks.bodies.CriticBody method) (aitraineree.networks.bodies.FcNet method) (aitraineree.networks.bodies.NoisyLayer method) (aitraineree.networks.bodies.NoisyNet method) (aitraineree.networks.heads.CategoricalNet method) (aitraineree.networks.heads.DuelingNet method) (aitraineree.networks.heads.RainbowNet method) (aitraineree.policies.BetaPolicy method) (aitraineree.policies.GaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicySimple method) (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) (aitraineree.tasks.GymTask method) (aitraineree.tasks.MultiAgentUnityTask method) (aitraineree.tasks.PettingZooTask method)

A

act() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.networks.heads.DoubleCritic method) (aitraineree.networks.heads.DuelingNet method) (aitraineree.networks.heads.RainbowNet method) (aitraineree.policies.MultivariateGaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicySimple method) action_max (aitraineree.agents.d3pg.D3PGAgent property) (aitraineree.agents.d4pg.D4PGAgent property) (aitraineree.agents.ddpg.DDPGAgent property) (aitraineree.agents.sac.SACAgent property) action_min (aitraineree.agents.d3pg.D3PGAgent property) (aitraineree.agents.d4pg.D4PGAgent property) (aitraineree.agents.ddpg.DDPGAgent property) (aitraineree.agents.sac.SACAgent property)

ActorBody (in module aitraineree.networks.bodies) add() (aitraineree.buffers.per.PERBuffer method) (aitraineree.buffers.replay.BufferBase method) (aitraineree.buffers.replay.ReplayBuffer method) (aitraineree.buffers.rollout.RolloutBuffer method) aitraineree.networks.bodies module aitraineree.networks.heads module aitraineree.policies module aitraineree.tasks module all_iterations (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner attribute) all_scores (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner attribute) alpha (aitraineree.agents.sac.SACAgent property)

B

BetaPolicy (class in aitraineree.policies)

BufferBase (class in aitraineree.buffers.replay)

C

CategoricalNet (class in aitraineree.networks.heads) clear() (aitraineree.buffers.replay.ReplayBuffer method) close() (aitraineree.tasks.MultiAgentUnityTask method) commit() (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) compute_policy_loss() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.sac.SACAgent method)

compute_value_loss() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.sac.SACAgent method) ConvNet (class in aitraineree.networks.bodies) create_env() (aitraineree.tasks.GymTask method) CriticBody (class in aitraineree.networks.bodies)

D

D3PGAgent (class in aitraineree.agents.d3pg) D4PGAgent (class in aitraineree.agents.d4pg) data_logger (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner attribute) DDPGAgent (class in aitraineree.agents.ddpg) detect_game_over() (aitraineree.tasks.MultiAgentUnityTask method) DeterministicPolicy (class in aitraineree.policies) diag_idx() (aitraineree.policies.MultivariateGaussianPolicy static method) (aitraineree.policies.MultivariateGaussianPolicySimple static method) DirichletPolicy (class in aitraineree.policies)

dist_projection() (aitraineree.networks.heads.CategoricalNet method) (aitraineree.networks.heads.RainbowNet method) DoubleCritic (class in aitraineree.networks.heads) DQNAgent (class in aitraineree.agents.dqn) DuelingNet (class in aitraineree.networks.heads) dump_buffer() (aitraineree.buffers.per.PERBuffer method) (aitraineree.buffers.replay.BufferBase method) (aitraineree.buffers.replay.ReplayBuffer method) (aitraineree.buffers.rollout.RolloutBuffer method)

E

EnvRunner (class in aitraineree.runners.env_runner)

Experience (class in aitraineree.types.experience)

F

FcNet (class in aitraineree.networks.bodies) forward() (aitraineree.networks.bodies.ConvNet method) (aitraineree.networks.bodies.CriticBody method) (aitraineree.networks.bodies.FcNet method) (aitraineree.networks.bodies.NoisyLayer method) (aitraineree.networks.bodies.NoisyNet method) (aitraineree.networks.bodies.ScaleNet method) (aitraineree.networks.heads.CategoricalNet method) (aitraineree.networks.heads.DoubleCritic method) (aitraineree.networks.heads.DuelingNet method) (aitraineree.networks.heads.NetChainer method) (aitraineree.networks.heads.RainbowNet method) (aitraineree.policies.BetaPolicy method) (aitraineree.policies.DeterministicPolicy method) (aitraineree.policies.DirichletPolicy method) (aitraineree.policies.GaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicySimple method)

from_state() (aitraineree.agents.ddpg.DDPGAgent static method) (aitraineree.agents.dqn.DQNAgent static method) (aitraineree.agents.ppo.PPOAgent static method) (aitraineree.agents.rainbow.RainbowAgent static method) (aitraineree.agents.sac.SACAgent static method)

G

GaussianPolicy (class in aitraineree.policies) get_network_state() (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) get_state() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method)

GymTask (class in aitraineree.tasks)

H

hidden_init() (in module aitraineree.networks.bodies)

I

info() (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method)

interact_episode() (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) IQLAgents (class in aitraineree.multi_agents.iql)

L

layer_init() (in module aitraineree.networks.bodies) learn() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) load_buffer() (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.buffers.per.PERBuffer method) (aitraineree.buffers.replay.BufferBase method) (aitraineree.buffers.replay.ReplayBuffer method) (aitraineree.buffers.rollout.RolloutBuffer method) load_state() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) log_data_interaction() (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) log_episode_metrics() (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method)

log_logger() (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) log_metrics() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) log_prob() (aitraineree.policies.BetaPolicy method) (aitraineree.policies.DirichletPolicy method) (aitraineree.policies.GaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicy method) (aitraineree.policies.MultivariateGaussianPolicySimple method) logger (aitraineree.agents.ppo.PPOAgent attribute) (aitraineree.runners.env_runner.EnvRunner attribute) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner attribute) loss (aitraineree.agents.d3pg.D3PGAgent property) (aitraineree.agents.d4pg.D4PGAgent property) (aitraineree.agents.ddpg.DDPGAgent property) (aitraineree.agents.dqn.DQNAgent property) (aitraineree.agents.ppo.PPOAgent property) (aitraineree.agents.rainbow.RainbowAgent property) (aitraineree.agents.sac.SACAgent property) (aitraineree.multi_agents.iql.IQLAgents property) (aitraineree.multi_agents.maddpg.MADDPGAgent property)

M

MADDPGAgent (class in aitraineree.multi_agents.maddpg) mean() (aitraineree.networks.heads.CategoricalNet method) model (aitraineree.agents.d3pg.D3PGAgent attribute) (aitraineree.agents.d4pg.D4PGAgent attribute) (aitraineree.agents.ddpg.DDPGAgent attribute) (aitraineree.agents.dqn.DQNAgent attribute) (aitraineree.agents.ppo.PPOAgent attribute) (aitraineree.agents.rainbow.RainbowAgent attribute) (aitraineree.agents.sac.SACAgent attribute) (aitraineree.multi_agents.iql.IQLAgents attribute) (aitraineree.multi_agents.maddpg.MADDPGAgent attribute)

module aitraineree.networks.bodies aitraineree.networks.heads aitraineree.policies aitraineree.tasks multi_agent (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner attribute) MultiAgentCycleEnvRunner (class in aitraineree.runners.multiagent_env_runner) MultiAgentEnvRunner (class in aitraineree.runners.multiagent_env_runner) MultiAgentUnityTask (class in aitraineree.tasks) MultivariateGaussianPolicy (class in aitraineree.policies) MultivariateGaussianPolicySimple (class in aitraineree.policies)

N

NetChainer (class in aitraineree.networks.heads) noise_function() (aitraineree.networks.bodies.NoisyLayer static method)

NoisyLayer (class in aitraineree.networks.bodies) NoisyNet (class in aitraineree.networks.bodies)

O

output_size (aitraineree.networks.bodies.ConvNet property)

P

param_dim (aitraineree.policies.BetaPolicy attribute) (aitraineree.policies.DeterministicPolicy attribute) (aitraineree.policies.DirichletPolicy attribute) (aitraineree.policies.MultivariateGaussianPolicy attribute) (aitraineree.policies.MultivariateGaussianPolicySimple attribute) (aitraineree.policies.PolicyType attribute)

PERBuffer (class in aitraineree.buffers.per) PettingZooTask (class in aitraineree.tasks) PolicyType (class in aitraineree.policies) PPOAgent (class in aitraineree.agents.ppo) priority_update() (aitraineree.buffers.per.PERBuffer method)

R

RainbowAgent (class in aitraineree.agents.rainbow) RainbowNet (class in aitraineree.networks.heads) render() (aitraineree.tasks.MultiAgentUnityTask method) ReplayBuffer (class in aitraineree.buffers.replay) reset() (aitraineree.agents.dqn.DQNAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) (aitraineree.tasks.MultiAgentUnityTask method) reset_agent() (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.sac.SACAgent method) reset_agents() (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) reset_alpha() (aitraineree.buffers.per.PERBuffer method)

reset_noise() (aitraineree.networks.bodies.NoisyLayer method) (aitraineree.networks.bodies.NoisyNet method) (aitraineree.networks.heads.NetChainer method) (aitraineree.networks.heads.RainbowNet method) reset_parameters() (aitraineree.networks.bodies.ConvNet method) (aitraineree.networks.bodies.CriticBody method) (aitraineree.networks.bodies.FcNet method) (aitraineree.networks.bodies.NoisyLayer method) (aitraineree.networks.bodies.NoisyNet method) (aitraineree.networks.heads.DoubleCritic method) (aitraineree.networks.heads.DuelingNet method) (aitraineree.networks.heads.NetChainer method) reset_paramters() (aitraineree.networks.heads.CategoricalNet method) RolloutBuffer (class in aitraineree.buffers.rollout) run() (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method)

S

SACAgent (class in aitraineree.agents.sac) sample() (aitraineree.buffers.per.PERBuffer method) (aitraineree.buffers.replay.BufferBase method) (aitraineree.buffers.replay.ReplayBuffer method) (aitraineree.buffers.rollout.RolloutBuffer method) save_buffer() (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.rainbow.RainbowAgent method) save_state() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) ScaleNet (class in aitraineree.networks.bodies) seed() (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.runners.env_runner.EnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentCycleEnvRunner method) (aitraineree.runners.multiagent_env_runner.MultiAgentEnvRunner method) (aitraineree.tasks.MultiAgentUnityTask method) set_buffer() (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method)

set_network() (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) state_dict() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) step() (aitraineree.agents.d3pg.D3PGAgent method) (aitraineree.agents.d4pg.D4PGAgent method) (aitraineree.agents.ddpg.DDPGAgent method) (aitraineree.agents.dqn.DQNAgent method) (aitraineree.agents.ppo.PPOAgent method) (aitraineree.agents.rainbow.RainbowAgent method) (aitraineree.agents.sac.SACAgent method) (aitraineree.multi_agents.iql.IQLAgents method) (aitraineree.multi_agents.maddpg.MADDPGAgent method) (aitraineree.tasks.GymTask method) (aitraineree.tasks.MultiAgentUnityTask method)

T

train_agent() (aitraineree.agents.ppo.PPOAgent method)

U

update_targets() (aitraineree.multi_agents.maddpg.MADDPGAgent method)