Functions — github.com/ShangtongZhang/reinforcement-learning-an-introduction

hub / github.com/ShangtongZhang/reinforcement-learning-an-introduction / functions

Functions359 in github.com/ShangtongZhang/reinforcement-learning-an-introduction

⨍ Functions 359◇ Types & classes 46

Functionbehavior_policy_player

(usable_ace_player, player_sum, dealer_card)

chapter05/blackjack.py:34

Methodcost_per_ep_hist

(self)

chapter12/lambda_effect.py:961

Methodcost_per_ep_hist

(self)

chapter12/lambda_effect.py:1083

Methodcost_to_go

(self, position, velocity)

chapter12/mountain_car.py:220

Methoddraw

(self)

chapter12/lambda_effect.py:871

Functiondutch_trace

(trace, active_tiles, lam, alpha)

chapter12/mountain_car.py:149

Methodempty

(self)

chapter08/maze.py:263

Methodepisode_end

(self, last_reward)

chapter13/short_corridor.py:138

Methoderror_hist

(self)

chapter12/lambda_effect.py:246

Methoderror_hist

(self)

chapter12/lambda_effect.py:322

Methodexpected_return_pe

(self, policy, values, state)

chapter04/car_rental_synchronous.py:179

Methodexpected_return_pi

(self, values, action, state)

chapter04/car_rental_synchronous.py:186

Methodfeed

(self, state, action, next_state, reward)

chapter08/maze.py:182

Methodfeed

(self, state, action, next_state, reward)

chapter08/maze.py:275

Methodfull

(self)

chapter10/access_control.py:35

Methodfull

(self)

chapter10/mountain_car.py:34

Methodfullp

(self)

chapter12/lambda_effect.py:78

Methodget_active_features

Get an array containing the id of the current active feature.

chapter12/lambda_effect.py:270

Methodget_active_features

Get an array containing the ids of the current active features.

chapter12/lambda_effect.py:433

Methodget_active_features

Get an array containing the ids of the current active features.

chapter12/lambda_effect.py:1005

Methodget_p_right

(self)

chapter13/short_corridor.py:95

Functionget_puddle_world_map

Creates the puddle world map and save the figure in the local folder as a .png file.

chapter12/lambda_effect.py:1094

Methodheight

(self)

chapter12/lambda_effect.py:808

Methodis_state_valid

(self, state)

chapter12/lambda_effect.py:563

Methodis_state_valid

(self, state)

chapter12/lambda_effect.py:649

Methodlearn

(self, state, reward)

chapter12/random_walk.py:72

Methodlearn

(self, state, reward)

chapter12/random_walk.py:127

Methodlearn

(self, state, reward)

chapter12/random_walk.py:149

Methodn_failures

(self)

chapter12/lambda_effect.py:633

Methodn_failures

(self)

chapter12/lambda_effect.py:779

Methodn_step_hist

(self)

chapter12/lambda_effect.py:401

Methodn_step_hist

(self)

chapter12/lambda_effect.py:529

Methodnew_episode

(self)

chapter12/random_walk.py:66

Methodnew_episode

(self)

chapter12/random_walk.py:141

Functionon_policy

(task, eval_interval)

chapter08/trajectory_sampling.py:95

Functionprioritized_sweeping

(q_value, model, maze, dyna_params)

chapter08/maze.py:340

Functionreplacing_trace

(trace, activeTiles, lam)

chapter12/mountain_car.py:124

Functionreplacing_trace_with_clearing

(trace, active_tiles, lam, clearing_tiles)

chapter12/mountain_car.py:136

Methodreset

(self)

chapter01/tic_tac_toe.py:187

Methodreset

(self)

chapter01/tic_tac_toe.py:269

Methodrun_sarsa_lambda

Apply Sarsa(λ) algorithm. (p.305) :param env: environment to interact with. :param n_episodes: number of episodes to train on.

chapter12/lambda_effect.py:437

Methodrun_sarsa_lambda

Apply Sarsa(λ) algorithm. (p.305) :param env: environment to interact with. :param n_episodes: number of episodes to train on.

chapter12/lambda_effect.py:1009

Methodsample

(self)

chapter08/maze.py:190

Methodsample

(self)

chapter08/maze.py:267

Methodset_state

(self, state)

chapter01/tic_tac_toe.py:272

Methodset_symbol

(self, symbol)

chapter01/tic_tac_toe.py:275

Functionsoftmax

(x)

chapter13/short_corridor.py:60

Methodstep

(self, state, action)

chapter12/lambda_effect.py:214

Methodstep

(self, state, action)

chapter12/lambda_effect.py:350

Methodstep

(self, state, action)

chapter12/lambda_effect.py:920

Functiontarget_policy

(state)

chapter11/counterexample.py:47

Functiontarget_policy

()

chapter05/infinite_variance.py:22

Functiontileswrap

Returns num-tilings tile indices corresponding to the floats and ints, wrapping some floats

chapter12/lambda_effect.py:122

Functionuniform

(task, eval_interval)

chapter08/trajectory_sampling.py:75

Methodupdate

(self, delta, state)

chapter09/random_walk.py:138

Methodupdate

(self, delta, state)

chapter09/random_walk.py:177

Methodvalue

(self, state)

chapter09/random_walk.py:126

Methodvalue

(self, state)

chapter09/random_walk.py:170

Methodwidth

(self)

chapter12/lambda_effect.py:812

← previous301–359 of 359, ranked by callers