Index

_

__init__() (A2CBuilder method) (A2CNetwork method) (AgentBuilder method) (BBOBuilder method) (BenchmarkExperiment method) (BenchmarkLogger method) (BenchmarkSuite method) (BenchmarkSuiteVisualizer method) (BenchmarkVisualizer method) (ConstrainedREPSBuilder method) (COPDAC_QBuilder method) (DDPGActorNetwork method) (DDPGBuilder method) (DDPGCriticNetwork method) (DoubleQLearningBuilder method) (DQNBuilder method) (EnvironmentBuilder method) (PGPEBuilder method) (PolicyGradientBuilder method) (PPOBuilder method) (QLearningBuilder method) (REPSBuilder method) (RWRBuilder method) (SACActorNetwork method) (SACBuilder method) (SACCriticNetwork method) (SARSABuilder method) (SarsaLambdaContinuousBuilder method) (SpeedyQLearningBuilder method) (StochasticACBuilder method) (TD3ActorNetwork method) (TD3Builder method) (TD3CriticNetwork method) (TDFiniteBuilder method) (TDTraceBuilder method) (TRPOBuilder method) (TRPONetwork method) (TrueOnlineSarsaLambdaBuilder method) (WeightedQLearningBuilder method)

A

A2CBuilder (class in mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.a2c) A2CNetwork (class in mushroom_rl_benchmark.builders.network.a2c_network) add_agent() (BenchmarkSuite method) add_environment() (BenchmarkSuite method) add_experiments() (BenchmarkSuite method) add_experiments_sweeps() (BenchmarkSuite method) add_sweep() (BenchmarkSuite method) AgentBuilder (class in mushroom_rl_benchmark.builders.agent_builder) aggregate_results() (in module mushroom_rl_benchmark.experiment.slurm.aggregate_results) alg_class (ConstrainedREPSBuilder attribute) (DoubleQLearningBuilder attribute) (eNACBuilder attribute) (GPOMDPBuilder attribute) (PGPEBuilder attribute) (QLambdaBuilder attribute) (QLearningBuilder attribute) (REINFORCEBuilder attribute) (REPSBuilder attribute) (RWRBuilder attribute) (SARSABuilder attribute) (SARSALambdaBuilder attribute) (SpeedyQLearningBuilder attribute) (WeightedQLearningBuilder attribute)

AveragedDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.averaged_dqn)

B

BBOBuilder (class in mushroom_rl_benchmark.builders.policy_search.black_box_optimization) BenchmarkExperiment (class in mushroom_rl_benchmark.core.experiment) BenchmarkLogger (class in mushroom_rl_benchmark.core.logger) BenchmarkSuite (class in mushroom_rl_benchmark.core.suite) BenchmarkSuiteVisualizer (class in mushroom_rl_benchmark.core.suite_visualizer) BenchmarkVisualizer (class in mushroom_rl_benchmark.core.visualizer) build() (A2CBuilder method) (AgentBuilder method) (AveragedDQNBuilder method) (BBOBuilder method) (CategoricalDQNBuilder method) (COPDAC_QBuilder method) (DDPGBuilder method) (DoubleDQNBuilder method) (DQNBuilder method) (DuelingDQNBuilder method) (EnvironmentBuilder method) (MaxminDQNBuilder method) (NoisyDQNBuilder method) (PolicyGradientBuilder method) (PPOBuilder method) (PrioritizedDQNBuilder method) (SACBuilder method) (SarsaLambdaContinuousBuilder method) (StochasticACBuilder method) (TD3Builder method) (TDFiniteBuilder method) (TRPOBuilder method) (TrueOnlineSarsaLambdaBuilder method)

build_sweep_dict() (in module mushroom_rl_benchmark.utils.sweep) build_sweep_list() (in module mushroom_rl_benchmark.utils.sweep)

C

CategoricalDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.categorical_dqn) compute_metrics() (in module mushroom_rl_benchmark.experiment.run) compute_Q() (A2CBuilder method) (AgentBuilder method) (BBOBuilder method) (COPDAC_QBuilder method) (DDPGBuilder method) (DoubleQLearningBuilder method) (DQNBuilder method) (PolicyGradientBuilder method) (PPOBuilder method) (SACBuilder method) (StochasticACBuilder method) (TD3Builder method) (TDFiniteBuilder method) (TRPOBuilder method)

ConstrainedREPSBuilder (class in mushroom_rl_benchmark.builders.policy_search.black_box_optimization) COPDAC_QBuilder (class in mushroom_rl_benchmark.builders.actor_critic.classic_actor_critic.copdac_q) copy() (AgentBuilder method) (EnvironmentBuilder method) create_slurm_script() (in module mushroom_rl_benchmark.experiment.slurm.slurm_script)

D

DDPGActorNetwork (class in mushroom_rl_benchmark.builders.network.ddpg_network) DDPGBuilder (class in mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.ddpg) DDPGCriticNetwork (class in mushroom_rl_benchmark.builders.network.ddpg_network) default() (A2CBuilder class method) (AgentBuilder class method) (AveragedDQNBuilder class method) (BBOBuilder class method) (CategoricalDQNBuilder class method) (ConstrainedREPSBuilder class method) (COPDAC_QBuilder class method) (DDPGBuilder class method) (DQNBuilder class method) (DuelingDQNBuilder class method) (MaxminDQNBuilder class method) (NoisyDQNBuilder class method) (PGPEBuilder class method) (PolicyGradientBuilder class method) (PPOBuilder class method) (PrioritizedDQNBuilder class method) (REPSBuilder class method) (RWRBuilder class method) (SACBuilder class method) (SarsaLambdaContinuousBuilder class method) (StochasticACBuilder class method) (TD3Builder class method) (TDFiniteBuilder class method) (TDTraceBuilder class method) (TRPOBuilder class method) (TrueOnlineSarsaLambdaBuilder class method) (WeightedQLearningBuilder class method)

dictionary_to_primitive() (in module mushroom_rl_benchmark.utils.primitive) DoubleDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.double_dqn) DoubleQLearningBuilder (class in mushroom_rl_benchmark.builders.value.td.td_finite) DQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.dqn) DuelingDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.dueling_dqn)

E

eNACBuilder (class in mushroom_rl_benchmark.builders.policy_search.policy_gradient) EnvironmentBuilder (class in mushroom_rl_benchmark.builders.environment_builder) exec_run() (in module mushroom_rl_benchmark.experiment.run) exists_best_agent() (BenchmarkLogger method) exists_policy_entropy() (BenchmarkLogger method) exists_stats() (BenchmarkLogger method)

exists_value_function() (BenchmarkLogger method) extend_and_save_entropy() (BenchmarkExperiment method) extend_and_save_J() (BenchmarkExperiment method) extend_and_save_R() (BenchmarkExperiment method) extend_and_save_V() (BenchmarkExperiment method) extract_arguments() (in module mushroom_rl_benchmark.utils.utils)

F

forward() (A2CNetwork method) (DDPGActorNetwork method) (DDPGCriticNetwork method) (SACActorNetwork method) (SACCriticNetwork method) (TD3ActorNetwork method) (TD3CriticNetwork method) (TRPONetwork method)

from_path() (BenchmarkLogger class method) (BenchmarkVisualizer class method)

G

generate_slurm() (in module mushroom_rl_benchmark.experiment.slurm.slurm_script) generate_sweep() (in module mushroom_rl_benchmark.utils.sweep) generate_sweep_params() (in module mushroom_rl_benchmark.utils.sweep) get_boxplot() (BenchmarkSuiteVisualizer method) get_entropy() (BenchmarkVisualizer method) get_figure_path() (BenchmarkLogger method) get_fit_params() (AgentBuilder method) get_J() (BenchmarkVisualizer method) get_log_dir() (BenchmarkLogger method)

get_log_id() (BenchmarkLogger method) get_params_path() (BenchmarkLogger method) get_path() (BenchmarkLogger method) get_preprocessors() (AgentBuilder method) get_R() (BenchmarkVisualizer method) get_report() (BenchmarkSuiteVisualizer method) (BenchmarkVisualizer method) get_V() (BenchmarkVisualizer method) GPOMDPBuilder (class in mushroom_rl_benchmark.builders.policy_search.policy_gradient)

I

is_data_persisted (BenchmarkVisualizer property)

L

load_agent_builder() (BenchmarkLogger method) load_best_agent() (BenchmarkLogger method) load_config() (BenchmarkLogger method) load_entropy() (BenchmarkLogger method) load_environment_builder() (BenchmarkLogger method)

load_J() (BenchmarkLogger method) load_last_agent() (BenchmarkLogger method) load_R() (BenchmarkLogger method) load_stats() (BenchmarkLogger method) load_V() (BenchmarkLogger method)

M

make_arguments() (in module mushroom_rl_benchmark.experiment.slurm.arguments) MaxminDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.maxmin_dqn) module mushroom_rl_benchmark.builders.actor_critic.classic_actor_critic.copdac_q mushroom_rl_benchmark.builders.actor_critic.classic_actor_critic.stochastic_ac mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.a2c mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.ddpg mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.ppo mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.sac mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.td3 mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.trpo mushroom_rl_benchmark.builders.agent_builder mushroom_rl_benchmark.builders.environment_builder mushroom_rl_benchmark.builders.network.a2c_network mushroom_rl_benchmark.builders.network.ddpg_network mushroom_rl_benchmark.builders.network.sac_network mushroom_rl_benchmark.builders.network.td3_network mushroom_rl_benchmark.builders.network.trpo_network mushroom_rl_benchmark.builders.policy_search.black_box_optimization mushroom_rl_benchmark.builders.policy_search.policy_gradient mushroom_rl_benchmark.builders.value.dqn.averaged_dqn mushroom_rl_benchmark.builders.value.dqn.categorical_dqn mushroom_rl_benchmark.builders.value.dqn.double_dqn mushroom_rl_benchmark.builders.value.dqn.dqn mushroom_rl_benchmark.builders.value.dqn.dueling_dqn mushroom_rl_benchmark.builders.value.dqn.maxmin_dqn mushroom_rl_benchmark.builders.value.dqn.noisy_dqn mushroom_rl_benchmark.builders.value.dqn.prioritized_dqn mushroom_rl_benchmark.builders.value.td.sarsa_lambda_continuous mushroom_rl_benchmark.builders.value.td.td_finite mushroom_rl_benchmark.builders.value.td.td_trace mushroom_rl_benchmark.builders.value.td.true_online_sarsa_lambda mushroom_rl_benchmark.core.experiment mushroom_rl_benchmark.core.logger mushroom_rl_benchmark.core.suite mushroom_rl_benchmark.core.suite_visualizer mushroom_rl_benchmark.core.visualizer mushroom_rl_benchmark.experiment.run mushroom_rl_benchmark.experiment.slurm.aggregate_results mushroom_rl_benchmark.experiment.slurm.arguments mushroom_rl_benchmark.experiment.slurm.run_script mushroom_rl_benchmark.experiment.slurm.slurm_script mushroom_rl_benchmark.utils.primitive mushroom_rl_benchmark.utils.sweep mushroom_rl_benchmark.utils.utils mushroom_rl_benchmark.builders.actor_critic.classic_actor_critic.copdac_q module mushroom_rl_benchmark.builders.actor_critic.classic_actor_critic.stochastic_ac module mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.a2c module mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.ddpg module mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.ppo module mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.sac module mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.td3 module mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.trpo module mushroom_rl_benchmark.builders.agent_builder module mushroom_rl_benchmark.builders.environment_builder module

mushroom_rl_benchmark.builders.network.a2c_network module mushroom_rl_benchmark.builders.network.ddpg_network module mushroom_rl_benchmark.builders.network.sac_network module mushroom_rl_benchmark.builders.network.td3_network module mushroom_rl_benchmark.builders.network.trpo_network module mushroom_rl_benchmark.builders.policy_search.black_box_optimization module mushroom_rl_benchmark.builders.policy_search.policy_gradient module mushroom_rl_benchmark.builders.value.dqn.averaged_dqn module mushroom_rl_benchmark.builders.value.dqn.categorical_dqn module mushroom_rl_benchmark.builders.value.dqn.double_dqn module mushroom_rl_benchmark.builders.value.dqn.dqn module mushroom_rl_benchmark.builders.value.dqn.dueling_dqn module mushroom_rl_benchmark.builders.value.dqn.maxmin_dqn module mushroom_rl_benchmark.builders.value.dqn.noisy_dqn module mushroom_rl_benchmark.builders.value.dqn.prioritized_dqn module mushroom_rl_benchmark.builders.value.td.sarsa_lambda_continuous module mushroom_rl_benchmark.builders.value.td.td_finite module mushroom_rl_benchmark.builders.value.td.td_trace module mushroom_rl_benchmark.builders.value.td.true_online_sarsa_lambda module mushroom_rl_benchmark.core.experiment module mushroom_rl_benchmark.core.logger module mushroom_rl_benchmark.core.suite module mushroom_rl_benchmark.core.suite_visualizer module mushroom_rl_benchmark.core.visualizer module mushroom_rl_benchmark.experiment.run module mushroom_rl_benchmark.experiment.slurm.aggregate_results module mushroom_rl_benchmark.experiment.slurm.arguments module mushroom_rl_benchmark.experiment.slurm.run_script module mushroom_rl_benchmark.experiment.slurm.slurm_script module mushroom_rl_benchmark.utils.primitive module mushroom_rl_benchmark.utils.sweep module mushroom_rl_benchmark.utils.utils module

N

NoisyDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.noisy_dqn)

O

object_to_primitive() (in module mushroom_rl_benchmark.utils.primitive)

P

PGPEBuilder (class in mushroom_rl_benchmark.builders.policy_search.black_box_optimization) plot_counter (BenchmarkSuiteVisualizer attribute) (BenchmarkVisualizer attribute) PolicyGradientBuilder (class in mushroom_rl_benchmark.builders.policy_search.policy_gradient)

PPOBuilder (class in mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.ppo) print_experiments() (BenchmarkSuite method) print_metrics() (in module mushroom_rl_benchmark.experiment.run) PrioritizedDQNBuilder (class in mushroom_rl_benchmark.builders.value.dqn.prioritized_dqn)

Q

QLambdaBuilder (class in mushroom_rl_benchmark.builders.value.td.td_trace)

QLearningBuilder (class in mushroom_rl_benchmark.builders.value.td.td_finite)

R

read_arguments_aggregate() (in module mushroom_rl_benchmark.experiment.slurm.arguments) read_arguments_run() (in module mushroom_rl_benchmark.experiment.slurm.arguments) REINFORCEBuilder (class in mushroom_rl_benchmark.builders.policy_search.policy_gradient) REPSBuilder (class in mushroom_rl_benchmark.builders.policy_search.black_box_optimization) reset() (BenchmarkExperiment method) resume() (BenchmarkExperiment method)

run() (BenchmarkExperiment method) (BenchmarkSuite method) run_parallel() (BenchmarkExperiment method) run_sequential() (BenchmarkExperiment method) run_slurm() (BenchmarkExperiment method) RWRBuilder (class in mushroom_rl_benchmark.builders.policy_search.black_box_optimization)

S

SACActorNetwork (class in mushroom_rl_benchmark.builders.network.sac_network) SACBuilder (class in mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.sac) SACCriticNetwork (class in mushroom_rl_benchmark.builders.network.sac_network) SARSABuilder (class in mushroom_rl_benchmark.builders.value.td.td_finite) SARSALambdaBuilder (class in mushroom_rl_benchmark.builders.value.td.td_trace) SarsaLambdaContinuousBuilder (class in mushroom_rl_benchmark.builders.value.td.sarsa_lambda_continuous) save_agent_builder() (BenchmarkLogger method) save_best_agent() (BenchmarkLogger method) save_boxplots() (BenchmarkSuiteVisualizer method) save_builders() (BenchmarkExperiment method) save_config() (BenchmarkLogger method) save_entropy() (BenchmarkLogger method) save_environment_builder() (BenchmarkLogger method) save_figure() (BenchmarkLogger method) save_J() (BenchmarkLogger method) save_last_agent() (BenchmarkLogger method) save_parameters() (BenchmarkSuite method) save_params() (BenchmarkLogger method) save_plot() (BenchmarkExperiment method) save_plots() (BenchmarkSuite method) save_R() (BenchmarkLogger method) save_report() (BenchmarkVisualizer method)

save_reports() (BenchmarkSuiteVisualizer method) save_stats() (BenchmarkLogger method) save_V() (BenchmarkLogger method) set_and_save_config() (BenchmarkExperiment method) set_and_save_stats() (BenchmarkExperiment method) set_eval_mode() (AgentBuilder method) (COPDAC_QBuilder method) (DQNBuilder method) (EnvironmentBuilder static method) (TDFiniteBuilder method) set_log_dir() (BenchmarkLogger method) set_log_id() (BenchmarkLogger method) set_preprocessors() (AgentBuilder method) show_agent() (BenchmarkVisualizer method) show_plot() (BenchmarkExperiment method) show_plots() (BenchmarkSuite method) show_report() (BenchmarkVisualizer method) show_reports() (BenchmarkSuiteVisualizer method) SpeedyQLearningBuilder (class in mushroom_rl_benchmark.builders.value.td.td_finite) start_timer() (BenchmarkExperiment method) StochasticACBuilder (class in mushroom_rl_benchmark.builders.actor_critic.classic_actor_critic.stochastic_ac) stop_timer() (BenchmarkExperiment method)

T

TD3ActorNetwork (class in mushroom_rl_benchmark.builders.network.td3_network) TD3Builder (class in mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.td3) TD3CriticNetwork (class in mushroom_rl_benchmark.builders.network.td3_network) TDFiniteBuilder (class in mushroom_rl_benchmark.builders.value.td.td_finite)

TDTraceBuilder (class in mushroom_rl_benchmark.builders.value.td.td_trace) to_duration() (in module mushroom_rl_benchmark.experiment.slurm.slurm_script) TRPOBuilder (class in mushroom_rl_benchmark.builders.actor_critic.deep_actor_critic.trpo) TRPONetwork (class in mushroom_rl_benchmark.builders.network.trpo_network) TrueOnlineSarsaLambdaBuilder (class in mushroom_rl_benchmark.builders.value.td.true_online_sarsa_lambda)

W

WeightedQLearningBuilder (class in mushroom_rl_benchmark.builders.value.td.td_finite)