Index

A

action_space (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) action_value() (mpcrl.Agent method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method)

Adam (class in mpcrl.optim) add_points() (mpcrl.util.geometry.ConvexPolytopeUniformSampler method) Agent (class in mpcrl) AgentCallbackMixin (class in mpcrl.core.callbacks) append() (mpcrl.ExperienceReplay method) appendleft() (mpcrl.ExperienceReplay method) ask() (mpcrl.optim.GradientFreeOptimizer method)

B

BaseOptimizer (class in mpcrl.optim.base_optimizer)

bool_cycle() (in module mpcrl.util.iters)

C

CallbackMixin (class in mpcrl.core.callbacks) can_explore() (mpcrl.core.exploration.EpsilonGreedyExploration method) (mpcrl.core.exploration.ExplorationStrategy method) (mpcrl.core.exploration.GreedyExploration method) (mpcrl.core.exploration.NoExploration method) (mpcrl.core.exploration.OrnsteinUhlenbeckExploration method) (mpcrl.core.exploration.StepWiseExploration method) can_update() (mpcrl.UpdateStrategy method) cbf() (in module mpcrl.util.control) Chain (class in mpcrl.core.schedulers) cholesky_added_multiple_identity() (in module mpcrl.util.math) class_name() (mpcrl.wrappers.envs.MonitorEpisodes class method) (mpcrl.wrappers.envs.MonitorInfos class method) clear() (mpcrl.ExperienceReplay method) (mpcrl.LearnableParametersDict method) clip() (in module mpcrl.util.math) close() (mpcrl.util.geometry.ConvexPolytopeUniformSampler method) (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method)

ConvexPolytopeUniformSampler (class in mpcrl.util.geometry) copy() (mpcrl.ExperienceReplay method) (mpcrl.LearnableParametersDict method) cost_perturbation_method (mpcrl.Agent attribute) (mpcrl.GlobOptLearningAgent attribute) (mpcrl.LearningAgent attribute) (mpcrl.LstdDpgAgent attribute) (mpcrl.LstdQLearningAgent attribute) (mpcrl.RlLearningAgent attribute) cost_perturbation_parameter (mpcrl.Agent attribute) (mpcrl.GlobOptLearningAgent attribute) (mpcrl.LearningAgent attribute) (mpcrl.LstdDpgAgent attribute) (mpcrl.LstdQLearningAgent attribute) (mpcrl.RlLearningAgent attribute) count() (mpcrl.ExperienceReplay method)

D

dcbf() (in module mpcrl.util.control) detach_wrapper() (mpcrl.wrappers.agents.Evaluate method) (mpcrl.wrappers.agents.LearningWrapper method) (mpcrl.wrappers.agents.Log method) (mpcrl.wrappers.agents.RecordUpdates method) (mpcrl.wrappers.agents.Wrapper method)

dlqr() (in module mpcrl.util.control) dual_norm() (in module mpcrl.util.math)

E

EpsilonGreedyExploration (class in mpcrl.core.exploration) Evaluate (class in mpcrl.wrappers.agents) evaluate() (mpcrl.Agent method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) experience (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property)

ExperienceReplay (class in mpcrl) exploration (mpcrl.Agent property) (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property) ExplorationStrategy (class in mpcrl.core.exploration) ExponentialScheduler (class in mpcrl.core.schedulers) extend() (mpcrl.ExperienceReplay method) extendleft() (mpcrl.ExperienceReplay method)

F

finalized_reset_infos() (mpcrl.wrappers.envs.MonitorInfos method) finalized_step_infos() (mpcrl.wrappers.envs.MonitorInfos method) fixed_parameters (mpcrl.Agent property) (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property)

force_episode_end() (mpcrl.wrappers.envs.MonitorEpisodes method) fromkeys() (mpcrl.LearnableParametersDict class method)

G

generate() (mpcrl.WarmStartStrategy method) get() (mpcrl.LearnableParametersDict method) get_wrapper_attr() (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method)

GlobOptLearningAgent (class in mpcrl) GradientBasedOptimizer (class in mpcrl.optim) GradientDescent (class in mpcrl.optim) GradientFreeOptimizer (class in mpcrl.optim) GreedyExploration (class in mpcrl.core.exploration)

H

has_wrapper_attr() (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method) hook (mpcrl.core.exploration.EpsilonGreedyExploration property) (mpcrl.core.exploration.ExplorationStrategy property) (mpcrl.core.exploration.GreedyExploration property) (mpcrl.core.exploration.NoExploration property) (mpcrl.core.exploration.OrnsteinUhlenbeckExploration property) (mpcrl.core.exploration.StepWiseExploration property) (mpcrl.optim.Adam property) (mpcrl.optim.GradientBasedOptimizer property) (mpcrl.optim.GradientDescent property) (mpcrl.optim.NewtonMethod property) (mpcrl.optim.RMSprop property)

I

iccbf() (in module mpcrl.util.control) index() (mpcrl.ExperienceReplay method) init_action_constraint (mpcrl.Agent attribute) (mpcrl.GlobOptLearningAgent attribute) (mpcrl.LearningAgent attribute) (mpcrl.LstdDpgAgent attribute) (mpcrl.LstdQLearningAgent attribute) (mpcrl.RlLearningAgent attribute) init_action_parameter (mpcrl.Agent attribute) (mpcrl.GlobOptLearningAgent attribute) (mpcrl.LearningAgent attribute) (mpcrl.LstdDpgAgent attribute) (mpcrl.LstdQLearningAgent attribute) (mpcrl.RlLearningAgent attribute)

insert() (mpcrl.ExperienceReplay method) is_wrapped() (mpcrl.Agent method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) (mpcrl.wrappers.agents.Evaluate method) (mpcrl.wrappers.agents.LearningWrapper method) (mpcrl.wrappers.agents.Log method) (mpcrl.wrappers.agents.RecordUpdates method) (mpcrl.wrappers.agents.Wrapper method) items() (mpcrl.LearnableParametersDict method)

K

keys() (mpcrl.LearnableParametersDict method)

L

lb (mpcrl.LearnableParametersDict property) learnable_parameters (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property) LearnableParameter (class in mpcrl) LearnableParametersDict (class in mpcrl) LearningAgent (class in mpcrl)

LearningAgentCallbackMixin (class in mpcrl.core.callbacks) LearningWrapper (class in mpcrl.wrappers.agents) lie_derivative() (in module mpcrl.util.math) LinearScheduler (class in mpcrl.core.schedulers) Log (class in mpcrl.wrappers.agents) LogLinearScheduler (class in mpcrl.core.schedulers) lqr() (in module mpcrl.util.control) LstdDpgAgent (class in mpcrl) LstdQLearningAgent (class in mpcrl)

M

maxlen (mpcrl.ExperienceReplay attribute) metadata (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) mk_seed() (in module mpcrl.util.seeding) mode (mpcrl.core.exploration.EpsilonGreedyExploration property) (mpcrl.core.exploration.ExplorationStrategy property) (mpcrl.core.exploration.GreedyExploration property) (mpcrl.core.exploration.NoExploration property) (mpcrl.core.exploration.OrnsteinUhlenbeckExploration property) (mpcrl.core.exploration.StepWiseExploration property) module mpcrl mpcrl.core mpcrl.core.callbacks mpcrl.core.errors mpcrl.core.experience mpcrl.core.exploration mpcrl.core.parameters mpcrl.core.schedulers mpcrl.core.update mpcrl.core.warmstart mpcrl.optim mpcrl.util mpcrl.util.control mpcrl.util.geometry mpcrl.util.iters mpcrl.util.math mpcrl.util.named mpcrl.util.seeding mpcrl.wrappers mpcrl.wrappers.agents mpcrl.wrappers.envs MonitorEpisodes (class in mpcrl.wrappers.envs) MonitorInfos (class in mpcrl.wrappers.envs) monomial_powers() (in module mpcrl.util.math) monomials_basis_function() (in module mpcrl.util.math) mpcrl module mpcrl.core module

mpcrl.core.callbacks module mpcrl.core.errors module mpcrl.core.experience module mpcrl.core.exploration module mpcrl.core.parameters module mpcrl.core.schedulers module mpcrl.core.update module mpcrl.core.warmstart module mpcrl.optim module mpcrl.util module mpcrl.util.control module mpcrl.util.geometry module mpcrl.util.iters module mpcrl.util.math module mpcrl.util.named module mpcrl.util.seeding module mpcrl.wrappers module mpcrl.wrappers.agents module mpcrl.wrappers.envs module MpcSolverError MpcSolverWarning

N

n_points (mpcrl.WarmStartStrategy property) Named (class in mpcrl.util.named) nchoosek() (in module mpcrl.util.math) NewtonMethod (class in mpcrl.optim) NoExploration (class in mpcrl.core.exploration)

NoScheduling (class in mpcrl.core.schedulers) np_random (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) np_random_seed (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property)

O

observation_space (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) on_env_step() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_episode_end() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_episode_start() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_mpc_failure() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_timestep_end() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_training_end() (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method)

on_training_start() (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_update() (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_update_failure() (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_validation_end() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) on_validation_start() (mpcrl.Agent method) (mpcrl.core.callbacks.AgentCallbackMixin method) (mpcrl.core.callbacks.LearningAgentCallbackMixin method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) order (mpcrl.optim.Adam property) (mpcrl.optim.GradientBasedOptimizer property) (mpcrl.optim.GradientDescent property) (mpcrl.optim.NewtonMethod property) (mpcrl.optim.RMSprop property) OrnsteinUhlenbeckExploration (class in mpcrl.core.exploration)

P

perturbation() (mpcrl.core.exploration.EpsilonGreedyExploration method) (mpcrl.core.exploration.ExplorationStrategy method) (mpcrl.core.exploration.GreedyExploration method) (mpcrl.core.exploration.NoExploration method) (mpcrl.core.exploration.OrnsteinUhlenbeckExploration method) (mpcrl.core.exploration.StepWiseExploration method)

pop() (mpcrl.ExperienceReplay method) (mpcrl.LearnableParametersDict method) popitem() (mpcrl.LearnableParametersDict method) popleft() (mpcrl.ExperienceReplay method) prefers_dict (mpcrl.optim.GradientFreeOptimizer attribute)

Q

Q (mpcrl.Agent property) (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property)

R

raise_or_warn_on_mpc_failure() (in module mpcrl.core.errors) raise_or_warn_on_update_failure() (in module mpcrl.core.errors) RecordUpdates (class in mpcrl.wrappers.agents) remove() (mpcrl.ExperienceReplay method) render() (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method) render_mode (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) reset() (mpcrl.Agent method) (mpcrl.core.exploration.EpsilonGreedyExploration method) (mpcrl.core.exploration.ExplorationStrategy method) (mpcrl.core.exploration.GreedyExploration method) (mpcrl.core.exploration.NoExploration method) (mpcrl.core.exploration.OrnsteinUhlenbeckExploration method) (mpcrl.core.exploration.StepWiseExploration method) (mpcrl.ExperienceReplay method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) (mpcrl.WarmStartStrategy method) (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method)

reverse() (mpcrl.ExperienceReplay method) rk4() (in module mpcrl.util.control) RlLearningAgent (class in mpcrl) RMSprop (class in mpcrl.optim) rotate() (mpcrl.ExperienceReplay method)

S

sample() (mpcrl.ExperienceReplay method) sample_from_interior() (mpcrl.util.geometry.ConvexPolytopeUniformSampler method) sample_from_surface() (mpcrl.util.geometry.ConvexPolytopeUniformSampler method) Scheduler (class in mpcrl.core.schedulers) seed() (mpcrl.util.geometry.ConvexPolytopeUniformSampler method) set_learnable_parameters() (mpcrl.optim.Adam method) (mpcrl.optim.base_optimizer.BaseOptimizer method) (mpcrl.optim.GradientBasedOptimizer method) (mpcrl.optim.GradientDescent method) (mpcrl.optim.GradientFreeOptimizer method) (mpcrl.optim.NewtonMethod method) (mpcrl.optim.RMSprop method) set_wrapper_attr() (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method) setdefault() (mpcrl.LearnableParametersDict method) size (mpcrl.LearnableParameter property) (mpcrl.LearnableParametersDict property) spec (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) state_value() (mpcrl.Agent method) (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) step() (mpcrl.core.exploration.EpsilonGreedyExploration method) (mpcrl.core.exploration.ExplorationStrategy method) (mpcrl.core.exploration.GreedyExploration method) (mpcrl.core.exploration.NoExploration method) (mpcrl.core.exploration.OrnsteinUhlenbeckExploration method) (mpcrl.core.exploration.StepWiseExploration method) (mpcrl.core.schedulers.Chain method) (mpcrl.core.schedulers.ExponentialScheduler method) (mpcrl.core.schedulers.LinearScheduler method) (mpcrl.core.schedulers.LogLinearScheduler method) (mpcrl.core.schedulers.NoScheduling method) (mpcrl.core.schedulers.Scheduler method) (mpcrl.optim.Adam method) (mpcrl.optim.GradientBasedOptimizer method) (mpcrl.optim.GradientDescent method) (mpcrl.optim.NewtonMethod method) (mpcrl.optim.RMSprop method) (mpcrl.wrappers.envs.MonitorEpisodes method) (mpcrl.wrappers.envs.MonitorInfos method)

StepWiseExploration (class in mpcrl.core.exploration) store_experience() (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) stringify() (mpcrl.LearnableParametersDict method) summarize_array() (in module mpcrl.util.math)

T

tell() (mpcrl.optim.GradientFreeOptimizer method) train() (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) train_offpolicy() (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method)

train_one_episode() (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method) train_one_rollout() (mpcrl.GlobOptLearningAgent method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.RlLearningAgent method)

U

ub (mpcrl.LearnableParametersDict property) unwrapped (mpcrl.Agent property) (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property) (mpcrl.wrappers.agents.Evaluate property) (mpcrl.wrappers.agents.LearningWrapper property) (mpcrl.wrappers.agents.Log property) (mpcrl.wrappers.agents.RecordUpdates property) (mpcrl.wrappers.agents.Wrapper property) (mpcrl.wrappers.envs.MonitorEpisodes property) (mpcrl.wrappers.envs.MonitorInfos property) update() (mpcrl.GlobOptLearningAgent method) (mpcrl.LearnableParametersDict method) (mpcrl.LearningAgent method) (mpcrl.LstdDpgAgent method) (mpcrl.LstdQLearningAgent method) (mpcrl.optim.Adam method) (mpcrl.optim.GradientBasedOptimizer method) (mpcrl.optim.GradientDescent method) (mpcrl.optim.NewtonMethod method) (mpcrl.optim.RMSprop method) (mpcrl.RlLearningAgent method)

update_strategy (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property) update_values() (mpcrl.LearnableParametersDict method) UpdateError UpdateStrategy (class in mpcrl) UpdateWarning

V

V (mpcrl.Agent property) (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property)

value (mpcrl.LearnableParametersDict property) value_as_dict (mpcrl.LearnableParametersDict property) values() (mpcrl.LearnableParametersDict method)

W

warmstart (mpcrl.Agent property) (mpcrl.GlobOptLearningAgent property) (mpcrl.LearningAgent property) (mpcrl.LstdDpgAgent property) (mpcrl.LstdQLearningAgent property) (mpcrl.RlLearningAgent property)

WarmStartStrategy (class in mpcrl) Wrapper (class in mpcrl.wrappers.agents) wrapper_spec() (mpcrl.wrappers.envs.MonitorEpisodes class method) (mpcrl.wrappers.envs.MonitorInfos class method)