Index

_

__init__() (l2rpn_baselines.DoNothing.DoNothing method) _action_size (l2rpn_baselines.utils.BaseDeepQ attribute) _lr (l2rpn_baselines.utils.BaseDeepQ attribute) _lr_decay_rate (l2rpn_baselines.utils.BaseDeepQ attribute) _lr_decay_steps (l2rpn_baselines.utils.BaseDeepQ attribute)

_model (l2rpn_baselines.utils.BaseDeepQ attribute) _nn_archi (l2rpn_baselines.utils.BaseDeepQ attribute) _observation_size (l2rpn_baselines.utils.BaseDeepQ attribute) _target_model (l2rpn_baselines.utils.BaseDeepQ attribute) _training_param (l2rpn_baselines.utils.BaseDeepQ attribute)

A

act() (l2rpn_baselines.DoNothing.DoNothing method) (l2rpn_baselines.Template.Template method) (l2rpn_baselines.utils.GymAgent method) action_size (l2rpn_baselines.utils.NNParam attribute) activs (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) (l2rpn_baselines.utils.NNParam attribute)

activs_policy (l2rpn_baselines.SACOld.SACOld_NNParam attribute) (l2rpn_baselines.SACOld.sacOld_NNParam.SACOld_NNParam attribute) activs_value (l2rpn_baselines.SACOld.SACOld_NNParam attribute) (l2rpn_baselines.SACOld.sacOld_NNParam.SACOld_NNParam attribute) add() (l2rpn_baselines.utils.ReplayBuffer method) apply_heuristics_actions() (l2rpn_baselines.utils.GymEnvWithHeuristics method)

B

BaseDeepQ (class in l2rpn_baselines.utils)

buffer_size (l2rpn_baselines.utils.TrainingParam attribute) build() (l2rpn_baselines.utils.GymAgent method)

C

center_reduce() (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam method) (l2rpn_baselines.utils.NNParam method) clean_heuristic_actions() (l2rpn_baselines.utils.GymAgent method) cli_eval() (in module l2rpn_baselines.utils) cli_train() (in module l2rpn_baselines.utils) compute_dims() (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam method) construct_q_network() (l2rpn_baselines.DeepQSimple.deepQ_NN.DeepQ_NN method) (l2rpn_baselines.DuelQLeapNet.DuelQLeapNet_NN method) (l2rpn_baselines.DuelQLeapNet.duelQLeapNet_NN.DuelQLeapNet_NN method) (l2rpn_baselines.DuelQSimple.duelQ_NN.DuelQ_NN method) (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.SACOld.sacOld_NN.SACOld_NN method) (l2rpn_baselines.utils.BaseDeepQ method)

convert_act() (l2rpn_baselines.DoubleDuelingDQN.DoubleDuelingDQN method) (l2rpn_baselines.DoubleDuelingRDQN.DoubleDuelingRDQN method) convert_obs() (l2rpn_baselines.DoubleDuelingDQN.DoubleDuelingDQN method) (l2rpn_baselines.DoubleDuelingRDQN.DoubleDuelingRDQN method) (l2rpn_baselines.utils.DeepQAgent method)

D

deep_q (l2rpn_baselines.utils.DeepQAgent attribute) DeepQ_NN (class in l2rpn_baselines.DeepQSimple.deepQ_NN) DeepQ_NNParam (class in l2rpn_baselines.DeepQSimple) DeepQAgent (class in l2rpn_baselines.utils) DeepQSimple (class in l2rpn_baselines.DeepQSimple) default_max_iter_fun() (l2rpn_baselines.utils.TrainingParam method) dict_action (l2rpn_baselines.utils.DeepQAgent attribute) dim_topo (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) discount_factor (l2rpn_baselines.utils.TrainingParam attribute) do_train() (l2rpn_baselines.utils.TrainingParam method) DoNothing (class in l2rpn_baselines.DoNothing) DoubleDuelingDQN (class in l2rpn_baselines.DoubleDuelingDQN)

DoubleDuelingDQN_NN (class in l2rpn_baselines.DoubleDuelingDQN.doubleDuelingDQN_NN) DoubleDuelingDQNConfig (class in l2rpn_baselines.DoubleDuelingDQN) DoubleDuelingRDQN (class in l2rpn_baselines.DoubleDuelingRDQN) DoubleDuelingRDQN_NN (class in l2rpn_baselines.DoubleDuelingRDQN.doubleDuelingRDQN_NN) DoubleDuelingRDQNConfig (class in l2rpn_baselines.DoubleDuelingRDQN) DuelQ_NN (class in l2rpn_baselines.DuelQSimple.duelQ_NN) DuelQ_NNParam (class in l2rpn_baselines.DuelQSimple) (class in l2rpn_baselines.DuelQSimple.duelQ_NNParam) DuelQLeapNet (class in l2rpn_baselines.DuelQLeapNet) DuelQLeapNet_NN (class in l2rpn_baselines.DuelQLeapNet) (class in l2rpn_baselines.DuelQLeapNet.duelQLeapNet_NN) DuelQSimple (class in l2rpn_baselines.DuelQSimple)

E

env_init (in module l2rpn_baselines.utils) Env_RLLIB (class in l2rpn_baselines.PPO_RLLIB) epsilon (l2rpn_baselines.utils.DeepQAgent attribute) evaluate() (in module l2rpn_baselines.DeepQSimple) (in module l2rpn_baselines.DoubleDuelingRDQN) (in module l2rpn_baselines.DuelQLeapNet) (in module l2rpn_baselines.DuelQSimple) (in module l2rpn_baselines.LeapNetEncoded) (in module l2rpn_baselines.PPO_RLLIB) (in module l2rpn_baselines.PPO_SB3) (in module l2rpn_baselines.SACOld) (in module l2rpn_baselines.Template)

F

filter_action_fun (l2rpn_baselines.utils.DeepQAgent attribute) final_epsilon (l2rpn_baselines.utils.TrainingParam attribute) fix_action() (l2rpn_baselines.utils.GymEnvWithHeuristics method)

from_dict() (l2rpn_baselines.utils.NNParam class method) (l2rpn_baselines.utils.TrainingParam static method) from_json() (l2rpn_baselines.utils.NNParam class method) (l2rpn_baselines.utils.TrainingParam static method)

G

get_act() (l2rpn_baselines.utils.GymAgent method) get_action_size() (l2rpn_baselines.utils.DeepQAgent static method) get_next_epsilon() (l2rpn_baselines.utils.TrainingParam method) get_obs_attr() (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam method) (l2rpn_baselines.utils.NNParam method)

get_obs_size() (l2rpn_baselines.utils.NNParam static method) get_path_model() (l2rpn_baselines.utils.BaseDeepQ static method) (l2rpn_baselines.utils.NNParam class method) GymAgent (class in l2rpn_baselines.utils) GymEnvWithHeuristics (class in l2rpn_baselines.utils) GymEnvWithReco (class in l2rpn_baselines.utils) GymEnvWithRecoWithDN (class in l2rpn_baselines.utils)

H

heuristic_actions() (l2rpn_baselines.utils.GymEnvWithHeuristics method) (l2rpn_baselines.utils.GymEnvWithReco method) (l2rpn_baselines.utils.GymEnvWithRecoWithDN method)

I

init_obs_extraction() (l2rpn_baselines.utils.DeepQAgent method)

initial_epsilon (l2rpn_baselines.utils.TrainingParam attribute) istraining (l2rpn_baselines.utils.DeepQAgent attribute)

L

l2rpn_baselines.DeepQSimple module l2rpn_baselines.DoNothing module l2rpn_baselines.DoubleDuelingDQN module l2rpn_baselines.DoubleDuelingDQN.doubleDuelingDQNConfig.DoubleDuelingDQNConfig module l2rpn_baselines.DoubleDuelingRDQN module l2rpn_baselines.DoubleDuelingRDQN.doubleDuelingRDQNConfig.DoubleDuelingRDQNConfig module l2rpn_baselines.DuelQLeapNet module l2rpn_baselines.DuelQSimple module l2rpn_baselines.ExpertAgent.ExpertAgent module l2rpn_baselines.LeapNetEncoded module l2rpn_baselines.PPO_RLLIB module l2rpn_baselines.PPO_SB3 module l2rpn_baselines.SACOld module

l2rpn_baselines.Template module l2rpn_baselines.utils module LeapNet_NNParam (class in l2rpn_baselines.DuelQLeapNet.leapNet_NNParam) LeapNetEncoded (class in l2rpn_baselines.LeapNetEncoded) LeapNetEncoded_NN (class in l2rpn_baselines.LeapNetEncoded) (class in l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN) LeapNetEncoded_NNParam (class in l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam) list_attr_obs (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) (l2rpn_baselines.utils.NNParam attribute) list_attr_obs_gm_out (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) list_attr_obs_input_q (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) list_attr_obs_tau (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam attribute) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) list_attr_obs_x (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) load() (l2rpn_baselines.Template.Template method) (l2rpn_baselines.utils.DeepQAgent method) (l2rpn_baselines.utils.GymAgent method) load_network() (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.SACOld.sacOld_NN.SACOld_NN method) (l2rpn_baselines.utils.BaseDeepQ method) lr (l2rpn_baselines.utils.TrainingParam attribute) lr_decay_rate (l2rpn_baselines.utils.TrainingParam attribute) lr_decay_steps (l2rpn_baselines.utils.TrainingParam attribute)

M

make_multi_env() (in module l2rpn_baselines.utils) make_nn() (l2rpn_baselines.utils.NNParam method) make_optimiser() (l2rpn_baselines.utils.BaseDeepQ method) max_global_norm_grad (l2rpn_baselines.utils.TrainingParam attribute) max_iter (l2rpn_baselines.utils.TrainingParam attribute) max_iter_fun (l2rpn_baselines.utils.TrainingParam attribute) max_loss (l2rpn_baselines.utils.TrainingParam attribute) max_value_grad (l2rpn_baselines.utils.TrainingParam attribute) min_iter (l2rpn_baselines.utils.TrainingParam attribute) min_observation (l2rpn_baselines.utils.TrainingParam attribute) minibatch_size (l2rpn_baselines.utils.TrainingParam attribute) module l2rpn_baselines.DeepQSimple l2rpn_baselines.DoNothing l2rpn_baselines.DoubleDuelingDQN l2rpn_baselines.DoubleDuelingDQN.doubleDuelingDQNConfig.DoubleDuelingDQNConfig l2rpn_baselines.DoubleDuelingRDQN l2rpn_baselines.DoubleDuelingRDQN.doubleDuelingRDQNConfig.DoubleDuelingRDQNConfig l2rpn_baselines.DuelQLeapNet l2rpn_baselines.DuelQSimple l2rpn_baselines.ExpertAgent.ExpertAgent l2rpn_baselines.LeapNetEncoded l2rpn_baselines.PPO_RLLIB l2rpn_baselines.PPO_SB3 l2rpn_baselines.SACOld l2rpn_baselines.Template l2rpn_baselines.utils

my_act() (l2rpn_baselines.DoubleDuelingDQN.DoubleDuelingDQN method) (l2rpn_baselines.DoubleDuelingRDQN.DoubleDuelingRDQN method) (l2rpn_baselines.utils.DeepQAgent method)

N

name (l2rpn_baselines.utils.DeepQAgent attribute) nb_curtail (l2rpn_baselines.utils.DeepQAgent attribute) nb_do_nothing (l2rpn_baselines.utils.DeepQAgent attribute) nb_env (in module l2rpn_baselines.utils) nb_injection (l2rpn_baselines.utils.DeepQAgent attribute) nb_redispatching (l2rpn_baselines.utils.DeepQAgent attribute) nb_storage (l2rpn_baselines.utils.DeepQAgent attribute) nb_topology (l2rpn_baselines.utils.DeepQAgent attribute) nb_voltage (l2rpn_baselines.utils.DeepQAgent attribute)

nn_class (l2rpn_baselines.DeepQSimple.DeepQ_NNParam attribute) (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam attribute) (l2rpn_baselines.DuelQSimple.DuelQ_NNParam attribute) (l2rpn_baselines.DuelQSimple.duelQ_NNParam.DuelQ_NNParam attribute) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) (l2rpn_baselines.SACOld.SACOld_NNParam attribute) (l2rpn_baselines.SACOld.sacOld_NNParam.SACOld_NNParam attribute) (l2rpn_baselines.utils.NNParam attribute), [1] NNParam (class in l2rpn_baselines.utils) num_frames (l2rpn_baselines.utils.TrainingParam attribute)

O

obs (l2rpn_baselines.DoNothing.DoNothing attribute) (l2rpn_baselines.DoubleDuelingDQN.DoubleDuelingDQN attribute) (l2rpn_baselines.DoubleDuelingRDQN.DoubleDuelingRDQN attribute) (l2rpn_baselines.Template.Template attribute)

observation_size (l2rpn_baselines.utils.NNParam attribute) oversampling_rate (l2rpn_baselines.utils.TrainingParam attribute)

P

PPO_RLLIB (in module l2rpn_baselines.PPO_RLLIB) PPO_SB3 (in module l2rpn_baselines.PPO_SB3) predict_movement() (l2rpn_baselines.DuelQLeapNet.DuelQLeapNet_NN method) (l2rpn_baselines.DuelQLeapNet.duelQLeapNet_NN.DuelQLeapNet_NN method) (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.SACOld.sacOld_NN.SACOld_NN method) (l2rpn_baselines.utils.BaseDeepQ method)

R

random_sample_datetime_start (l2rpn_baselines.utils.TrainingParam attribute) remove_non_usable_attr() (in module l2rpn_baselines.PPO_SB3) replay_buffer (l2rpn_baselines.utils.DeepQAgent attribute) ReplayBuffer (class in l2rpn_baselines.utils) reset() (l2rpn_baselines.DoNothing.DoNothing method) (l2rpn_baselines.DoubleDuelingDQN.DoubleDuelingDQN method) (l2rpn_baselines.DoubleDuelingRDQN.DoubleDuelingRDQN method) (l2rpn_baselines.PPO_RLLIB.Env_RLLIB method) (l2rpn_baselines.Template.Template method) (l2rpn_baselines.utils.GymEnvWithHeuristics method)

S

SACOld (class in l2rpn_baselines.SACOld) SACOld_NN (class in l2rpn_baselines.SACOld.sacOld_NN) SACOld_NNParam (class in l2rpn_baselines.SACOld) (class in l2rpn_baselines.SACOld.sacOld_NNParam) sample() (l2rpn_baselines.utils.ReplayBuffer method) save() (l2rpn_baselines.Template.Template method) (l2rpn_baselines.utils.DeepQAgent method) save_as_json() (l2rpn_baselines.utils.NNParam method) (l2rpn_baselines.utils.TrainingParam method) save_log_gif() (in module l2rpn_baselines.utils) save_model_each (l2rpn_baselines.utils.TrainingParam attribute) save_network() (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.SACOld.sacOld_NN.SACOld_NN method) (l2rpn_baselines.utils.BaseDeepQ method) save_tensorboard() (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.utils.BaseDeepQ method)

save_used_attribute() (in module l2rpn_baselines.PPO_SB3) schedule_lr_model (l2rpn_baselines.DeepQSimple.deepQ_NN.DeepQ_NN attribute) sizes (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute) (l2rpn_baselines.utils.NNParam attribute) sizes_policy (l2rpn_baselines.SACOld.SACOld_NNParam attribute) (l2rpn_baselines.SACOld.sacOld_NNParam.SACOld_NNParam attribute) sizes_value (l2rpn_baselines.SACOld.SACOld_NNParam attribute) (l2rpn_baselines.SACOld.sacOld_NNParam.SACOld_NNParam attribute) step() (l2rpn_baselines.PPO_RLLIB.Env_RLLIB method) (l2rpn_baselines.utils.GymEnvWithHeuristics method) step_for_final_epsilon (l2rpn_baselines.utils.TrainingParam attribute) step_increase_nb_iter (l2rpn_baselines.utils.TrainingParam attribute) store_action (l2rpn_baselines.utils.DeepQAgent attribute) str2bool() (in module l2rpn_baselines.utils)

T

target_train() (l2rpn_baselines.SACOld.sacOld_NN.SACOld_NN method) (l2rpn_baselines.utils.BaseDeepQ method) tau (l2rpn_baselines.utils.TrainingParam attribute) tau_adds (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam attribute) tau_dims (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam attribute) tau_mults (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam attribute) tell_step() (l2rpn_baselines.utils.TrainingParam method) Template (class in l2rpn_baselines.Template) to_dict() (l2rpn_baselines.utils.NNParam method) (l2rpn_baselines.utils.TrainingParam method) train() (in module l2rpn_baselines.DeepQSimple) (in module l2rpn_baselines.DoubleDuelingRDQN) (in module l2rpn_baselines.DuelQLeapNet) (in module l2rpn_baselines.DuelQSimple) (in module l2rpn_baselines.LeapNetEncoded) (in module l2rpn_baselines.PPO_RLLIB) (in module l2rpn_baselines.PPO_SB3) (in module l2rpn_baselines.SACOld) (in module l2rpn_baselines.Template) (l2rpn_baselines.DuelQLeapNet.DuelQLeapNet_NN method) (l2rpn_baselines.DuelQLeapNet.duelQLeapNet_NN.DuelQLeapNet_NN method) (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.SACOld.sacOld_NN.SACOld_NN method) (l2rpn_baselines.Template.Template method) (l2rpn_baselines.utils.BaseDeepQ method) (l2rpn_baselines.utils.DeepQAgent method)

train_generic() (in module l2rpn_baselines.utils) train_on_batch() (l2rpn_baselines.DuelQLeapNet.DuelQLeapNet_NN method) (l2rpn_baselines.DuelQLeapNet.duelQLeapNet_NN.DuelQLeapNet_NN method) (l2rpn_baselines.LeapNetEncoded.LeapNetEncoded_NN method) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NN.LeapNetEncoded_NN method) (l2rpn_baselines.utils.BaseDeepQ method) TrainingParam (class in l2rpn_baselines.utils)

U

update_freq (l2rpn_baselines.utils.TrainingParam attribute)

update_nb_iter (l2rpn_baselines.utils.TrainingParam attribute) update_tensorboard_freq (l2rpn_baselines.utils.TrainingParam attribute)

V

verbose (l2rpn_baselines.utils.DeepQAgent attribute)

X

x_dim (l2rpn_baselines.DuelQLeapNet.leapNet_NNParam.LeapNet_NNParam attribute) (l2rpn_baselines.LeapNetEncoded.leapNetEncoded_NNParam.LeapNetEncoded_NNParam attribute)