| | |
|
a | |
 |
agents |
|
|
agents.actor_critic_agent |
|
|
agents.agent_base |
|
|
agents.dps_agent |
|
|
agents.dyna_td_agent |
|
|
agents.fitted_r_max_agent |
|
|
agents.mbdps_agent |
|
|
agents.monte_carlo_agent |
|
|
agents.random_agent |
|
|
agents.td_agent |
|
|
agents.td_lambda_agent |
|
| | |
|
e | |
|
environments |
|
|
environments.single_agent_environment |
|
| | |
|
f | |
|
framework |
|
|
framework.experiment |
|
|
framework.filesystem |
|
|
framework.interaction_server |
|
|
framework.monitor |
|
|
framework.observables |
|
|
framework.protocol |
|
|
framework.spaces |
|
|
framework.state |
|
|
framework.world |
|
| | |
|
m | |
|
mmlf |
|
| | |
|
r | |
|
resources |
|
|
resources.function_approximators.cmac |
|
|
resources.function_approximators.function_approximator |
|
|
resources.function_approximators.knn |
|
|
resources.function_approximators.linear_combination |
|
|
resources.function_approximators.mlp |
|
|
resources.function_approximators.multilinear_grid |
|
|
resources.function_approximators.qcon |
|
|
resources.function_approximators.rbf |
|
|
resources.function_approximators.tabular_storage |
|
|
resources.learning_algorithms.eligibility_traces |
|
|
resources.learning_algorithms.temporal_difference |
|
|
resources.model.grid_model |
|
|
resources.model.knn_model |
|
|
resources.model.lwpr_model |
|
|
resources.model.model |
|
|
resources.model.rmax_model_wrapper |
|
|
resources.model.tabular_model |
|
|
resources.optimization.cmaes_optimizer |
|
|
resources.optimization.evolution_strategy |
|
|
resources.optimization.optimizer |
|
|
resources.optimization.random_search |
|
|
resources.planner.mbdps_planner |
|
|
resources.planner.planner |
|
|
resources.planner.prioritized_sweeping |
|
|
resources.planner.trajectory_sampling |
|
|
resources.planner.value_iteration |
|
|
resources.policies.linear_policy |
|
|
resources.policies.mlp_policy |
|
|
resources.policies.policy |
|
|
resources.policies.value_function_policy |
|
|
resources.policy_search.fixed_parametrization |
|
|
resources.policy_search.policy_search |
|
|
resources.skill_discovery.skill_discovery |
|
| | |
|
w | |
|
worlds |
|
|
worlds.double_pole_balancing.environments.double_pole_balancing_environment |
|
|
worlds.linear_markov_chain.environments.linear_markov_chain_environment |
|
|
worlds.maze2d.environments.maze2d_environment |
|
|
worlds.maze_cliff.environments.maze_cliff_environment |
|
|
worlds.mountain_car.environments.mcar_env |
|
|
worlds.pinball_maze.environments.pinball_maze_environment |
|
|
worlds.po_double_pole_balancing.environments.po_double_pole_balancing_environment |
|
|
worlds.seventeen_and_four.environments.seventeen_and_four |
|
|
worlds.single_pole_balancing.environments.single_pole_balancing_environment |
|
