Index

A

A2C (class in all.agents) A2CTestAgent (class in all.agents) act() (all.agents.A2C method) (all.agents.A2CTestAgent method) (all.agents.Agent method) (all.agents.C51 method) (all.agents.C51TestAgent method) (all.agents.DDPG method) (all.agents.DDPGTestAgent method) (all.agents.DDQN method) (all.agents.DQN method) (all.agents.DQNTestAgent method) (all.agents.IndependentMultiagent method) (all.agents.Multiagent method) (all.agents.ParallelAgent method) (all.agents.PPO method) (all.agents.SAC method) (all.agents.SACTestAgent method) (all.agents.VAC method) (all.agents.VPG method) (all.agents.VQN method) (all.agents.VQNTestAgent method) (all.agents.VSarsa method) (all.bodies.Body method) action_space (all.environments.AtariEnvironment property) (all.environments.DuplicateEnvironment property) (all.environments.Environment property) (all.environments.GymEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.PybulletEnvironment property) (all.environments.VectorEnvironment property) action_space() (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) add_eval() (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method) add_hparams() (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method) add_info() (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method) add_loss() (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method) add_schedule() (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method) add_summary() (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method)

advantages() (all.memory.GeneralizedAdvantageBuffer method) (all.memory.NStepAdvantageBuffer method) agent (all.bodies.Body property) (all.core.MultiagentState property) Agent (class in all.agents) agent() (all.presets.IndependentMultiagentPreset method) (all.presets.ParallelPreset method) (all.presets.Preset method) agent_iter() (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) agent_selection (all.environments.MultiagentAtariEnv property) (all.environments.MultiagentPettingZooEnv property) Aggregation (class in all.nn) all.agents module all.approximation module all.bodies module all.core module all.environments module all.experiments module all.logging module all.memory module all.nn module all.optim module all.policies module all.presets module all.presets.atari module all.presets.classic_control module all.presets.continuous module apply() (all.core.State method) apply_mask() (all.core.State method) (all.core.StateArray method) Approximation (class in all.approximation) array() (all.core.State class method) as_input() (all.core.State method) (all.core.StateArray method) as_output() (all.core.State method) (all.core.StateArray method) AtariEnvironment (class in all.environments)

B

batch_execute() (all.core.StateArray method) Body (class in all.bodies)

build() (all.presets.ParallelPresetBuilder method) (all.presets.PresetBuilder method)

C

C51 (class in all.agents) C51TestAgent (class in all.agents) cat() (all.core.StateArray class method) CategoricalDueling (class in all.nn) Checkpointer (class in all.approximation) ClipRewards (class in all.bodies) close() (all.environments.AtariEnvironment method) (all.environments.DuplicateEnvironment method) (all.environments.Environment method) (all.environments.GymEnvironment method) (all.environments.GymVectorEnvironment method) (all.environments.MujocoEnvironment method) (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) (all.environments.PybulletEnvironment method) (all.environments.VectorEnvironment method) (all.experiments.Experiment method) (all.experiments.MultiagentEnvExperiment method) (all.logging.DummyLogger method) (all.logging.ExperimentLogger method) (all.logging.Logger method)

create_sbatch_script() (all.experiments.SlurmExperiment method)

D

DDPG (class in all.agents) DDPGTestAgent (class in all.agents) DDQN (class in all.agents) DDQNTestAgent (in module all.agents) DeepmindAtariBody (class in all.bodies) DeterministicPolicy (class in all.policies) device (all.environments.AtariEnvironment property) (all.environments.DuplicateEnvironment property) (all.environments.Environment property) (all.environments.GymEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.MultiagentAtariEnv property) (all.environments.MultiagentEnvironment property) (all.environments.MultiagentPettingZooEnv property) (all.environments.PybulletEnvironment property) (all.environments.VectorEnvironment property)

device() (all.presets.PresetBuilder method) done (all.core.State property) (all.core.StateArray property) DQN (class in all.agents) DQNTestAgent (class in all.agents) Dueling (class in all.nn) DummyCheckpointer (class in all.approximation) DummyLogger (class in all.logging) duplicate() (all.environments.AtariEnvironment method) (all.environments.Environment method) (all.environments.GymEnvironment method) (all.environments.MujocoEnvironment method) (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentPettingZooEnv method) (all.environments.PybulletEnvironment method) DuplicateEnvironment (class in all.environments)

E

env (all.environments.AtariEnvironment property) (all.environments.GymEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.PybulletEnvironment property) env() (all.presets.PresetBuilder method) Environment (class in all.environments) episode (all.experiments.Experiment property) (all.experiments.MultiagentEnvExperiment property) (all.experiments.ParallelEnvExperiment property) (all.experiments.SingleEnvExperiment property) eval() (all.agents.C51 method) (all.agents.DDPG method) (all.agents.DDQN method) (all.agents.DQN method) (all.agents.PPO method) (all.agents.VAC method) (all.agents.VPG method) (all.agents.VQN method) (all.agents.VSarsa method) (all.approximation.Approximation method) (all.bodies.Body method) (all.policies.GreedyPolicy method) (all.policies.ParallelGreedyPolicy method)

ExperienceReplayBuffer (class in all.memory) Experiment (class in all.experiments) ExperimentLogger (class in all.logging)

F

FeatureNetwork (class in all.approximation) FixedTarget (class in all.approximation) Flatten (class in all.nn) flatten() (all.core.StateArray method) Float (class in all.nn) forward() (all.nn.Aggregation method) (all.nn.CategoricalDueling method) (all.nn.Dueling method) (all.nn.Flatten method) (all.nn.Float method) (all.nn.NoisyFactorizedLinear method) (all.nn.NoisyLinear method) (all.nn.RLNetwork method) (all.nn.Scale method) (all.nn.TanhActionBound method)

frame (all.experiments.Experiment property) (all.experiments.MultiagentEnvExperiment property) (all.experiments.ParallelEnvExperiment property) (all.experiments.SingleEnvExperiment property) FrameStack (class in all.bodies) from_gym() (all.core.State class method) from_zoo() (all.core.MultiagentState class method)

G

GaussianPolicy (class in all.policies) GeneralizedAdvantageBuffer (class in all.memory)

GreedyPolicy (class in all.policies) GymEnvironment (class in all.environments) GymVectorEnvironment (class in all.environments)

H

hyperparameters() (all.presets.PresetBuilder method)

I

Identity (class in all.approximation) IndependentMultiagent (class in all.agents) IndependentMultiagentPreset (class in all.presets) init() (all.approximation.Checkpointer method) (all.approximation.DummyCheckpointer method) (all.approximation.FixedTarget method) (all.approximation.PeriodicCheckpointer method) (all.approximation.PolyakTarget method) (all.approximation.TargetNetwork method) (all.approximation.TrivialTarget method)

is_done() (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method)

L

last() (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) Linear0 (class in all.nn)

LinearScheduler (class in all.optim) load_and_watch() (in module all.experiments) log_dir (all.logging.Logger attribute) Logger (class in all.logging)

M

make_output_directory() (all.experiments.SlurmExperiment method) mask (all.core.State property) (all.core.StateArray property) module all.agents all.approximation all.bodies all.core all.environments all.experiments all.logging all.memory all.nn all.optim all.policies all.presets all.presets.atari all.presets.classic_control all.presets.continuous

MujocoEnvironment (class in all.environments) Multiagent (class in all.agents) MultiagentAtariEnv (class in all.environments) MultiagentEnvExperiment (class in all.experiments) MultiagentEnvironment (class in all.environments) MultiagentPettingZooEnv (class in all.environments) MultiagentState (class in all.core)

N

n_envs (all.presets.ParallelPreset property) name (all.environments.AtariEnvironment property) (all.environments.DuplicateEnvironment property) (all.environments.Environment property) (all.environments.GymEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.MultiagentAtariEnv property) (all.environments.MultiagentEnvironment property) (all.environments.MultiagentPettingZooEnv property) (all.environments.PybulletEnvironment property) (all.environments.VectorEnvironment property)

name() (all.presets.PresetBuilder method) no_grad() (all.approximation.Approximation method) (all.policies.GreedyPolicy method) (all.policies.ParallelGreedyPolicy method) NoisyFactorizedLinear (class in all.nn) NoisyLinear (class in all.nn) NStepAdvantageBuffer (class in all.memory) NStepReplayBuffer (class in all.memory) num_envs (all.environments.DuplicateEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.VectorEnvironment property)

O

observation (all.core.State property) (all.core.StateArray property) observation_space (all.environments.AtariEnvironment property) (all.environments.DuplicateEnvironment property) (all.environments.Environment property) (all.environments.GymEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.PybulletEnvironment property) (all.environments.VectorEnvironment property)

observation_space() (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method)

P

parallel_test_agent() (all.presets.ParallelPreset method) ParallelAgent (class in all.agents) ParallelEnvExperiment (class in all.experiments) ParallelGreedyPolicy (class in all.policies) ParallelPreset (class in all.presets) ParallelPresetBuilder (class in all.presets) parse_args() (all.experiments.SlurmExperiment method) PeriodicCheckpointer (class in all.approximation) plot_returns_100() (in module all.experiments) PolyakTarget (class in all.approximation) PPO (class in all.agents)

PPOTestAgent (in module all.agents) Preset (class in all.presets) PresetBuilder (class in all.presets) PrioritizedReplayBuffer (class in all.memory) process_action() (all.bodies.Body method) process_state() (all.bodies.Body method) (all.bodies.ClipRewards method) (all.bodies.FrameStack method) (all.bodies.TimeFeature method) project() (all.approximation.QDist method) PybulletEnvironment (class in all.environments)

Q

QContinuous (class in all.approximation) QDist (class in all.approximation)

QNetwork (class in all.approximation) queue_jobs() (all.experiments.SlurmExperiment method)

R

Rainbow (class in all.agents) RainbowTestAgent (in module all.agents) reinforce() (all.approximation.Approximation method) (all.approximation.Identity method) render() (all.environments.AtariEnvironment method) (all.environments.Environment method) (all.environments.GymEnvironment method) (all.environments.MujocoEnvironment method) (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) (all.environments.PybulletEnvironment method) ReplayBuffer (class in all.memory) reset() (all.environments.AtariEnvironment method) (all.environments.DuplicateEnvironment method) (all.environments.Environment method) (all.environments.GymEnvironment method) (all.environments.GymVectorEnvironment method) (all.environments.MujocoEnvironment method) (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) (all.environments.PybulletEnvironment method) (all.environments.VectorEnvironment method)

reset_parameters() (all.nn.Linear0 method) (all.nn.NoisyFactorizedLinear method) (all.nn.NoisyLinear method) reward (all.core.State property) (all.core.StateArray property) RLNetwork (class in all.nn) run_experiment() (all.experiments.SlurmExperiment method) (in module all.experiments) run_sbatch_script() (all.experiments.SlurmExperiment method)

S

SAC (class in all.agents) SACTestAgent (class in all.agents) sample() (all.memory.ExperienceReplayBuffer method) (all.memory.NStepReplayBuffer method) (all.memory.PrioritizedReplayBuffer method) (all.memory.ReplayBuffer method) save() (all.experiments.Experiment method) (all.experiments.MultiagentEnvExperiment method) (all.presets.ParallelPreset method) (all.presets.Preset method) Scale (class in all.nn) Schedulable (class in all.optim) seed() (all.environments.AtariEnvironment method) (all.environments.GymEnvironment method) (all.environments.MujocoEnvironment method) (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentPettingZooEnv method) (all.environments.PybulletEnvironment method) shape (all.core.State property) (all.core.StateArray property) short_names (all.environments.PybulletEnvironment attribute) SingleEnvExperiment (class in all.experiments) SlurmExperiment (class in all.experiments) SoftDeterministicPolicy (class in all.policies) SoftmaxPolicy (class in all.policies) state (all.environments.AtariEnvironment property) (all.environments.Environment property) (all.environments.GymEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.MultiagentAtariEnv property) (all.environments.MultiagentEnvironment property) (all.environments.MultiagentPettingZooEnv property) (all.environments.PybulletEnvironment property) State (class in all.core)

state_array (all.environments.DuplicateEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.VectorEnvironment property) state_space (all.environments.AtariEnvironment property) (all.environments.DuplicateEnvironment property) (all.environments.Environment property) (all.environments.GymEnvironment property) (all.environments.GymVectorEnvironment property) (all.environments.MujocoEnvironment property) (all.environments.PybulletEnvironment property) (all.environments.VectorEnvironment property) state_space() (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) StateArray (class in all.core) step() (all.approximation.Approximation method) (all.approximation.Identity method) (all.environments.AtariEnvironment method) (all.environments.DuplicateEnvironment method) (all.environments.Environment method) (all.environments.GymEnvironment method) (all.environments.GymVectorEnvironment method) (all.environments.MujocoEnvironment method) (all.environments.MultiagentAtariEnv method) (all.environments.MultiagentEnvironment method) (all.environments.MultiagentPettingZooEnv method) (all.environments.PybulletEnvironment method) (all.environments.VectorEnvironment method) store() (all.memory.ExperienceReplayBuffer method) (all.memory.GeneralizedAdvantageBuffer method) (all.memory.NStepAdvantageBuffer method) (all.memory.NStepReplayBuffer method) (all.memory.PrioritizedReplayBuffer method) (all.memory.ReplayBuffer method)

T

TanhActionBound (class in all.nn) target() (all.approximation.Approximation method) TargetNetwork (class in all.approximation) td_loss() (in module all.nn) test() (all.experiments.Experiment method) (all.experiments.MultiagentEnvExperiment method) (all.experiments.ParallelEnvExperiment method) (all.experiments.SingleEnvExperiment method) test_agent() (all.presets.IndependentMultiagentPreset method) (all.presets.ParallelPreset method) (all.presets.Preset method)

TimeFeature (class in all.bodies) to() (all.core.MultiagentState method) (all.core.State method) train() (all.experiments.Experiment method) (all.experiments.MultiagentEnvExperiment method) (all.experiments.ParallelEnvExperiment method) (all.experiments.SingleEnvExperiment method) TrivialTarget (class in all.approximation)

U

update() (all.approximation.FixedTarget method) (all.approximation.PolyakTarget method) (all.approximation.TargetNetwork method) (all.approximation.TrivialTarget method) (all.core.State method) (all.core.StateArray method)

update_priorities() (all.memory.ExperienceReplayBuffer method) (all.memory.NStepReplayBuffer method) (all.memory.PrioritizedReplayBuffer method) (all.memory.ReplayBuffer method)

V

VAC (class in all.agents) VACTestAgent (in module all.agents) VectorEnvironment (class in all.environments) view() (all.core.StateArray method) VNetwork (class in all.approximation)

VPG (class in all.agents) VPGTestAgent (in module all.agents) VQN (class in all.agents) VQNTestAgent (class in all.agents) VSarsa (class in all.agents) VSarsaTestAgent (in module all.agents)

W

watch() (in module all.experiments)

weighted_mse_loss() (in module all.nn) weighted_smooth_l1_loss() (in module all.nn)

Z

zero_grad() (all.approximation.Approximation method)