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

↓ 66 callersMethodplot

(self)

chapter04/car_rental_synchronous.py:193

↓ 8 callersMethodvalue

(self, state)

chapter09/random_walk.py:91

↓ 7 callersMethodvalue

(self, state)

chapter12/random_walk.py:45

↓ 6 callersFunctionget_card

()

chapter05/blackjack.py:47

↓ 6 callersMethodget_tiles

Get the encoded state_action using Sutton's grid tiling software.

chapter12/lambda_effect.py:153

↓ 5 callersFunctioncard_value

(card_id)

chapter05/blackjack.py:53

↓ 5 callersMethodfull

(self)

chapter12/mountain_car.py:32

↓ 5 callersMethodhash

(self)

chapter01/tic_tac_toe.py:31

↓ 5 callersFunctionsimulate

(runs, time, bandits)

chapter02/ten_armed_testbed.py:101

↓ 4 callersMethodget_pi

(self)

chapter13/short_corridor.py:80

↓ 4 callersFunctionpoisson

(n, lam)

chapter04/car_rental_synchronous.py:43

↓ 4 callersFunctionpoisson_probability

(n, lam)

chapter04/car_rental.py:56

↓ 4 callersFunctionsemi_gradient_n_step_sarsa

(value_function, n=1)

chapter10/mountain_car.py:172

↓ 4 callersMethodset_state

(self, state)

chapter01/tic_tac_toe.py:191

↓ 4 callersFunctionstep

(state, action)

chapter03/grid_world.py:34

↓ 4 callersMethodstep

(self, state, action)

chapter12/lambda_effect.py:574

↓ 4 callersFunctionupdate_trace_vector

Updates agent's trace vector (z) with then current state (or state-action pair) using to the given method. Returns the updated vector.

chapter12/lambda_effect.py:167

↓ 4 callersMethodvalue

(self, free_servers, priority, action)

chapter10/access_control.py:137

↓ 3 callersMethod__init__

(self, rate, step_size)

chapter12/random_walk.py:39

↓ 3 callersFunctionchoose_action

(state, q_value)

chapter06/cliff_walking.py:85

↓ 3 callersFunctioncompute_RMSVE

(theta)

chapter11/counterexample.py:179

↓ 3 callersFunctiondraw_image

(image)

chapter03/grid_world.py:50

↓ 3 callersMethodfeed

(self, state, action, next_state, reward)

chapter08/maze.py:216

↓ 3 callersMethodget_active_features

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

chapter12/lambda_effect.py:682

↓ 3 callersMethodget_active_tiles

(self, position, velocity, action)

chapter12/mountain_car.py:185

↓ 3 callersFunctiongradient_monte_carlo

(value_function, alpha, distribution=None)

chapter09/random_walk.py:188

↓ 3 callersMethodload_policy

(self)

chapter01/tic_tac_toe.py:253

↓ 3 callersMethodnext_state

(self, i, j, symbol)

chapter01/tic_tac_toe.py:82

↓ 3 callersFunctionparameter_sweep

(value_function_generator, runs, lambdas, alphas)

chapter12/random_walk.py:182

↓ 3 callersFunctionplay

(policy_player, initial_state=None, initial_action=None)

chapter05/blackjack.py:60

↓ 3 callersMethodplay

(self, print_state=False)

chapter01/tic_tac_toe.py:154

↓ 3 callersMethodprint_state

(self)

chapter01/tic_tac_toe.py:89

↓ 3 callersMethodq_hat

Compute the q value for the current state-action pair.

chapter12/lambda_effect.py:424

↓ 3 callersMethodq_hat

Compute the q value for the current state-action pair.

chapter12/lambda_effect.py:674

↓ 3 callersMethodq_hat

Compute the q value for the current state-action pair.

chapter12/lambda_effect.py:996

↓ 3 callersMethodreset

(self)

chapter01/tic_tac_toe.py:144

↓ 3 callersMethodrun_sarsa_lambda

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

chapter12/lambda_effect.py:686

↓ 3 callersFunctionsarsa

(q_value, expected=False, step_size=ALPHA)

chapter06/cliff_walking.py:97

↓ 3 callersMethodstep

(self, state, action)

chapter08/maze.py:120

↓ 3 callersFunctiontemporal_difference

(values, alpha=0.1, batch=False)

chapter06/random_walk.py:36

↓ 3 callersFunctiontrue_value

True value of the first state Args: p (float): probability of the action 'right'. Returns: True value of the first state.

chapter13/short_corridor.py:15

↓ 3 callersMethodv_hat

Returns the approximated value for state, w.r.t. the weight vector.

chapter12/lambda_effect.py:257

↓ 3 callersMethodvalue

(self, position, velocity, action)

chapter12/mountain_car.py:194

↓ 3 callersMethodvalue

(self, position, velocity, action)

chapter10/mountain_car.py:139

↓ 2 callersFunctionargmax

(value)

chapter08/trajectory_sampling.py:29

↓ 2 callersMethodbackup

(self)

chapter01/tic_tac_toe.py:211

↓ 2 callersFunctionbatch_updating

(method, episodes, alpha=0.001)

chapter06/random_walk.py:132

↓ 2 callersFunctionbehavior_policy

(state)

chapter11/counterexample.py:61

↓ 2 callersMethodbellman

(self, values, action, state)

chapter04/car_rental_synchronous.py:129

↓ 2 callersFunctionchanging_maze

(maze, dyna_params)

chapter08/maze.py:434

↓ 2 callersFunctionchoose_action

(state, q_value)

chapter06/maximization_bias.py:54

↓ 2 callersFunctionchoose_action

(state, q_value, maze, dyna_params)

chapter08/maze.py:167

↓ 2 callersFunctioncompute_RMSPBE

(theta)

chapter11/counterexample.py:184

↓ 2 callersFunctioncompute_state_value

(in_place=True, discount=1.0)

chapter04/grid_world.py:66

↓ 2 callersMethodcvt_ij2xy

(self, pos_ij)

chapter12/lambda_effect.py:868

↓ 2 callersFunctiondyna_q

(q_value, model, maze, dyna_params)

chapter08/maze.py:298

↓ 2 callersMethodempty

(self)

chapter08/maze.py:44

↓ 2 callersFunctionevaluate_pi

(q, task)

chapter08/trajectory_sampling.py:58

↓ 2 callersFunctionexpected_return

@state: [# of cars in first location, # of cars in second location] @action: positive if moving cars from first location to second location,

chapter04/car_rental.py:64

↓ 2 callersMethodextend_state

(self, state, factor)

chapter08/maze.py:94

↓ 2 callersFunctionget_action

(position, velocity, valueFunction)

chapter12/mountain_car.py:227

↓ 2 callersFunctionget_action

(free_servers, priority, value_function)

chapter10/access_control.py:161

↓ 2 callersFunctionget_action

(position, velocity, value_function)

chapter10/mountain_car.py:161

↓ 2 callersFunctionget_action

()

chapter09/random_walk.py:75

↓ 2 callersMethodget_active_features

(self, x)

chapter09/square_wave.py:73

↓ 2 callersMethodget_active_tiles

(self, free_servers, priority, action)

chapter10/access_control.py:130

↓ 2 callersMethodget_active_tiles

(self, position, velocity, action)

chapter10/mountain_car.py:130

↓ 2 callersMethodget_dist2puddle

Get state's distance (float) to the nearest puddle's border. Returns a float corresponding to the state's distance to the nearest puddle borde

chapter12/lambda_effect.py:821

↓ 2 callersFunctionhashcoords

(coordinates, m, readonly=False)

chapter12/lambda_effect.py:98

↓ 2 callersMethodinsert

(self, priority, state, action)

chapter08/maze.py:258

↓ 2 callersMethodis_end

(self)

chapter01/tic_tac_toe.py:39

↓ 2 callersMethodis_state_goal

(self, state)

chapter12/lambda_effect.py:815

↓ 2 callersMethodis_state_over_bounds

Returns True if the current state is out of bounds, i.e. the current run is over. Returns False otherwise.

chapter12/lambda_effect.py:662

↓ 2 callersMethodis_terminal_state

(self, state)

chapter12/lambda_effect.py:993

↓ 2 callersFunctionmonte_carlo

(values, alpha=0.1, batch=False)

chapter06/random_walk.py:60

↓ 2 callersFunctionmonte_carlo_on_policy

(episodes)

chapter05/blackjack.py:181

↓ 2 callersFunctionplay

(evaluator)

chapter12/mountain_car.py:237

↓ 2 callersMethodpolicy

Apply a ε-greedy policy to choose an action from state.

chapter12/lambda_effect.py:404

↓ 2 callersMethodpolicy

Apply a ε-greedy policy to choose an action from state.

chapter12/lambda_effect.py:636

↓ 2 callersMethodpolicy

Apply a ε-greedy policy to choose an action from state.

chapter12/lambda_effect.py:964

↓ 2 callersFunctionprint_optimal_policy

(q_value)

chapter06/cliff_walking.py:143

↓ 2 callersFunctionq_learning

(q_value, step_size=ALPHA)

chapter06/cliff_walking.py:128

↓ 2 callersFunctionq_learning

(q1, q2=None)

chapter06/maximization_bias.py:69

↓ 2 callersMethodreset

(self)

chapter13/short_corridor.py:33

↓ 2 callersMethodsample

(self)

chapter08/maze.py:233

↓ 2 callersMethodsave_policy

(self)

chapter01/tic_tac_toe.py:249

↓ 2 callersFunctionsemi_gradient_temporal_difference

(value_function, n, alpha)

chapter09/random_walk.py:211

↓ 2 callersMethodset_symbol

(self, symbol)

chapter01/tic_tac_toe.py:195

↓ 2 callersMethodsize

(self)

chapter09/square_wave.py:28

↓ 2 callersMethodsolve

(self)

chapter04/car_rental_synchronous.py:63

↓ 2 callersFunctionstep

(state, action)

chapter06/cliff_walking.py:41

↓ 2 callersFunctionstep

(state, action)

chapter11/counterexample.py:41

↓ 2 callersFunctionstep

(state, action)

chapter09/random_walk.py:61

↓ 2 callersMethodstep

(self, state, action)

chapter08/trajectory_sampling.py:49

↓ 2 callersFunctiontrial

(num_episodes, agent_generator)

chapter13/short_corridor.py:164

↓ 2 callersMethodupdate

(self, delta, state)

chapter09/random_walk.py:100

↓ 2 callersMethodvalue

(self, x)

chapter09/square_wave.py:81

↓ 1 callersFunctionTDC

(state, theta, weight, alpha, beta)

chapter11/counterexample.py:110

↓ 1 callersMethod__init__

(self)

chapter13/short_corridor.py:30

↓ 1 callersMethod__init__

(self)

chapter08/maze.py:51

next →1–100 of 359, ranked by callers