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

↓ 1 callersFunctionhash_coords

(coordinates, m, read_only=False)

chapter10/access_control.py:54

↓ 1 callersFunctionhash_coords

(coordinates, m, read_only=False)

chapter10/mountain_car.py:53

↓ 1 callersFunctionis_terminal

(state)

chapter04/grid_world.py:25

↓ 1 callersMethodis_terminal_state

(self, state)

chapter12/lambda_effect.py:421

↓ 1 callersMethodlambda_return_from_time

(self, time)

chapter12/random_walk.py:92

↓ 1 callersMethodlearn

(self, position, velocity, action, target)

chapter12/mountain_car.py:201

↓ 1 callersMethodlearn

(self, state, reward)

chapter12/random_walk.py:50

↓ 1 callersMethodlearn

(self, free_servers, priority, action, new_free_servers, new_priority, new_action, reward)

chapter10/access_control.py:150

↓ 1 callersMethodlearn

(self, position, velocity, action, target)

chapter10/mountain_car.py:146

↓ 1 callersFunctionmonte_carlo_es

(episodes)

chapter05/blackjack.py:202

↓ 1 callersFunctionmonte_carlo_off_policy

(episodes)

chapter05/blackjack.py:243

↓ 1 callersMethodn_step_return_from_time

(self, n, time)

chapter12/random_walk.py:82

↓ 1 callersMethodnew_episode

(self)

chapter12/random_walk.py:56

↓ 1 callersMethodnew_episode

(self)

chapter12/random_walk.py:121

↓ 1 callersMethodoff_line_learn

(self)

chapter12/random_walk.py:107

↓ 1 callersFunctionplay

()

chapter01/tic_tac_toe.py:328

↓ 1 callersFunctionplay

()

chapter05/infinite_variance.py:26

↓ 1 callersMethodpolicy

Action selection : uniform distribution. State argument is given for consistency.

chapter12/lambda_effect.py:253

↓ 1 callersMethodpolicy_evaluation

(self, values, policy)

chapter04/car_rental_synchronous.py:83

↓ 1 callersMethodpolicy_improvement

(self, actions, values, policy)

chapter04/car_rental_synchronous.py:107

↓ 1 callersMethodpop_item

(self)

chapter08/maze.py:36

↓ 1 callersMethodpredecessor

(self, state)

chapter08/maze.py:284

↓ 1 callersFunctionprint_cost

(value_function, episode, ax)

chapter10/mountain_car.py:234

↓ 1 callersFunctionrandom_walk

(value_function)

chapter12/random_walk.py:163

↓ 1 callersMethodremove_item

(self, item)

chapter08/maze.py:32

↓ 1 callersMethodreset

(self)

chapter02/ten_armed_testbed.py:43

↓ 1 callersFunctionrms_error

()

chapter06/random_walk.py:100

↓ 1 callersMethodrun_td_lambda

Method described p293 of the book. :param env: environment to interact with. :param n_episodes: number of episodes to train on.

chapter12/lambda_effect.py:274

↓ 1 callersFunctionsample

(n)

chapter09/square_wave.py:41

↓ 1 callersFunctionsemi_gradient_DP

(theta, alpha)

chapter11/counterexample.py:89

↓ 1 callersFunctionsemi_gradient_off_policy_TD

(state, theta, alpha)

chapter11/counterexample.py:71

↓ 1 callersFunctionsquare_wave

(x)

chapter09/square_wave.py:35

↓ 1 callersMethodstate_value

(self, free_servers, priority)

chapter10/access_control.py:142

↓ 1 callersFunctionstep

(state, action)

chapter06/windy_grid_world.py:42

↓ 1 callersFunctionstep

(state, action)

chapter04/grid_world.py:30

↓ 1 callersFunctionstep

(position, velocity, action)

chapter12/mountain_car.py:99

↓ 1 callersFunctionstep

(position, velocity, action)

chapter10/mountain_car.py:95

↓ 1 callersMethodstep

(self, action)

chapter02/ten_armed_testbed.py:77

↓ 1 callersMethodstep

Args: go_right (bool): chosen action Returns: tuple of (reward, episode terminated?)

chapter13/short_corridor.py:36

↓ 1 callersFunctiontake_action

(state, action)

chapter06/maximization_bias.py:62

↓ 1 callersFunctiontake_action

(free_servers, priority, action)

chapter10/access_control.py:171

↓ 1 callersFunctiontarget_policy_player

(usable_ace_player, player_sum, dealer_card)

chapter05/blackjack.py:30

↓ 1 callersFunctiontemporal_difference

(value, n, alpha)

chapter07/random_walk.py:40

↓ 1 callersFunctiontiles

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

chapter12/lambda_effect.py:106

↓ 1 callersFunctiontiles

returns num-tilings tile indices corresponding to the floats and ints

chapter12/mountain_car.py:56

↓ 1 callersFunctiontiles

returns num-tilings tile indices corresponding to the floats and ints

chapter10/access_control.py:59

↓ 1 callersFunctiontiles

returns num-tilings tile indices corresponding to the floats and ints

chapter10/mountain_car.py:58

↓ 1 callersFunctiontrain

(epochs, print_every_n=500)

chapter01/tic_tac_toe.py:287

↓ 1 callersMethodtrain

(self, n_episodes, method)

chapter12/lambda_effect.py:325

↓ 1 callersMethodtrain

(self, n_episodes, method)

chapter12/lambda_effect.py:532

↓ 1 callersMethodtrain

(self, n_step_max, method)

chapter12/lambda_effect.py:782

↓ 1 callersMethodtrain

(self, n_episodes, method)

chapter12/lambda_effect.py:1089

↓ 1 callersMethodupdate

(self, delta, x)

chapter09/square_wave.py:87

Method__init__

(self, truncate, parallel_processes, delta=1e-2, gamma=0.9, solve_4_5=False)

chapter04/car_rental_synchronous.py:52

Method__init__

(self)

chapter01/tic_tac_toe.py:20

Method__init__

(self, player1, player2)

chapter01/tic_tac_toe.py:134

Method__init__

(self, step_size=0.1, epsilon=0.1)

chapter01/tic_tac_toe.py:179

Method__init__

(self, **kwargs)

chapter01/tic_tac_toe.py:264

Method__init__

(self, k_arm=10, epsilon=0., initial=0., step_size=0.1, sample_averages=False, UCB_param=None,

chapter02/ten_armed_testbed.py:28

Method__init__

(self, sizeval)

chapter12/lambda_effect.py:63

Method__init__

(self, iht_size, num_tilings, tiling_size, obs_bounds)

chapter12/lambda_effect.py:141

Method__init__

(self)

chapter12/lambda_effect.py:204

Method__init__

(self, lmbda, alpha)

chapter12/lambda_effect.py:221

Method__init__

(self, lmbda, alpha)

chapter12/lambda_effect.py:317

Method__init__

(self)

chapter12/lambda_effect.py:336

Method__init__

(self, alpha, lmbda, iht_args)

chapter12/lambda_effect.py:369

Method__init__

(self, lmbda, alpha)

chapter12/lambda_effect.py:508

Method__init__

(self)

chapter12/lambda_effect.py:544

Method__init__

(self, iht_args, alpha, lmbda)

chapter12/lambda_effect.py:604

Method__init__

(self, lmbda, alpha)

chapter12/lambda_effect.py:755

Method__init__

(self)

chapter12/lambda_effect.py:793

Method__init__

(self, grid)

chapter12/lambda_effect.py:908

Method__init__

(self, grid, alpha, lmbda, iht_args)

chapter12/lambda_effect.py:938

Method__init__

(self, lmbda, alpha)

chapter12/lambda_effect.py:1059

Method__init__

(self, size_val)

chapter12/mountain_car.py:24

Method__init__

(self, step_size, lam, trace_update=accumulating_trace, num_of_tilings=8, max_size=2048)

chapter12/mountain_car.py:163

Method__init__

(self, rate, step_size)

chapter12/random_walk.py:61

Method__init__

(self, rate, step_size)

chapter12/random_walk.py:117

Method__init__

(self, rate, step_size)

chapter12/random_walk.py:138

Method__init__

(self, alpha, gamma)

chapter13/short_corridor.py:69

Method__init__

(self, alpha, gamma, alpha_w)

chapter13/short_corridor.py:133

Method__init__

(self, size_val)

chapter10/access_control.py:27

Method__init__

(self, num_of_tilings, alpha=ALPHA, beta=BETA)

chapter10/access_control.py:112

Method__init__

(self, size_val)

chapter10/mountain_car.py:26

Method__init__

(self, step_size, num_of_tilings=8, max_size=2048)

chapter10/mountain_car.py:113

Method__init__

(self, left, right)

chapter09/square_wave.py:19

Method__init__

(self, feature_width, domain=DOMAIN, alpha=0.2, num_of_features=50)

chapter09/square_wave.py:53

Method__init__

(self, num_of_groups)

chapter09/random_walk.py:83

Method__init__

(self, numOfTilings, tileWidth, tilingOffset)

chapter09/random_walk.py:109

Method__init__

(self, order, type)

chapter09/random_walk.py:156

chapter08/maze.py:140

Method__init__

(self, rand=np.random)

chapter08/maze.py:177

Method__init__

(self, maze, time_weight=1e-4, rand=np.random)

chapter08/maze.py:205

Method__init__

(self, rand=np.random)

chapter08/maze.py:250

Method__init__

(self, n_states, b)

chapter08/trajectory_sampling.py:38

Method__str__

Prepares a string for printing whenever this object is printed.

chapter12/lambda_effect.py:68

Functionaccumulating_trace

(trace, active_tiles, lam)

chapter12/mountain_car.py:114

Methodact

(self)

chapter01/tic_tac_toe.py:278

Functionbehavior_policy

(usable_ace, player_sum, dealer_card)

chapter05/blackjack.py:209

← previous next →201–300 of 359, ranked by callers