Functions — github.com/Vincentzyx/Douzero

hub / github.com/Vincentzyx/Douzero_Resnet / functions

Functions168 in github.com/Vincentzyx/Douzero_Resnet

⨍ Functions 168◇ Types & classes 25

Method__init__

(self)

douzero/dmc/models.py:48

Method__init__

(self)

douzero/dmc/models.py:83

Method__init__

(self)

douzero/dmc/models.py:118

Method__init__

(self)

douzero/dmc/models.py:153

Method__init__

(self, in_planes, planes, stride=1)

douzero/dmc/models.py:226

Method__init__

(self)

douzero/dmc/models.py:253

Method__init__

(self)

douzero/dmc/models.py:304

Method__init__

(self, device=0)

douzero/dmc/models.py:361

Method__init__

(self, device=0)

douzero/dmc/models.py:401

Method__setstate__

(self, state)

douzero/radam/radam.py:113

Method__setstate__

(self, state)

douzero/radam/radam.py:189

Method_acting_player_position

The player that is active. It can be landlord, landlod_down, or landlord_up.

douzero/env/env.py:326

Method_game_bomb_num

The number of bombs played so far. This is used as a feature of the neural network and is also used to calculate ADP.

douzero/env/env.py:311

Method_game_infoset

Here, inforset is defined as all the information in the current situation, incuding the hand cards of all the players, all th

douzero/env/env.py:299

Method_game_over

Returns a Boolean

douzero/env/env.py:334

Method_game_winner

A string of landlord/peasants

douzero/env/env.py:320

Function_get_obs_for_bid_legacy

(player_id, bid_info, hand_cards)

douzero/env/env.py:1157

Function_get_obs_for_multiply

(position, bid_info, hand_cards, landlord_cards)

douzero/env/env.py:1301

Function_get_obs_general1

(infoset, position)

douzero/env/env.py:887

Function_get_obs_landlord_withbid

Obttain the landlord features. See Table 4 in https://arxiv.org/pdf/2106.06135.pdf

douzero/env/env.py:802

Functionact

(i, device, batch_queues, model, flags)

douzero/dmc/utils.py:74

Methodact

(self, infoset)

douzero/evaluation/deep_agent.py:35

Methodact

(self, infoset)

douzero/evaluation/random_agent.py:8

Methodact

(self, infoset)

douzero/evaluation/rlcard_agent.py:22

Functionbatch_and_learn

Thread target for the learning process.

douzero/dmc/dmc.py:150

Methodclose

(self)

douzero/dmc/env_utils.py:88

Methodeval

(self)

douzero/dmc/models.py:381

Methodeval

(self)

douzero/dmc/models.py:418

Functionfilter_type_10_serial_triple

(moves, rival_move)

douzero/env/move_selector.py:56

Functionfilter_type_11_serial_3_1

(moves, rival_move)

douzero/env/move_selector.py:59

Functionfilter_type_12_serial_3_2

(moves, rival_move)

douzero/env/move_selector.py:70

Functionfilter_type_13_4_2

(moves, rival_move)

douzero/env/move_selector.py:81

Functionfilter_type_14_4_22

(moves, rival_move)

douzero/env/move_selector.py:92

Functionfilter_type_1_single

(moves, rival_move)

douzero/env/move_selector.py:11

Functionfilter_type_2_pair

(moves, rival_move)

douzero/env/move_selector.py:15

Functionfilter_type_3_triple

(moves, rival_move)

douzero/env/move_selector.py:19

Functionfilter_type_4_bomb

(moves, rival_move)

douzero/env/move_selector.py:23

Functionfilter_type_6_3_1

(moves, rival_move)

douzero/env/move_selector.py:28

Functionfilter_type_7_3_2

(moves, rival_move)

douzero/env/move_selector.py:39

Functionfilter_type_8_serial_single

(moves, rival_move)

douzero/env/move_selector.py:50

Functionfilter_type_9_serial_pair

(moves, rival_move)

douzero/env/move_selector.py:53

(self, z, x, return_value=False, flags=None)

douzero/dmc/models.py:23

Methodforward

(self, z, x, return_value=False, flags=None)

douzero/dmc/models.py:58

Methodforward

(self, z, x, return_value=False, flags=None)

douzero/dmc/models.py:93

Methodforward

(self, z, x, return_value=False, flags=None)

douzero/dmc/models.py:128

Methodforward

(self, z, x, return_value=False, flags=None, debug=False)

douzero/dmc/models.py:188

Methodforward

(self, x)

douzero/dmc/models.py:244

Methodforward

(self, z, x, return_value=False, flags=None, debug=False)

douzero/dmc/models.py:279

Methodforward

(self, z, x, return_value=False, flags=None, debug=False)

douzero/dmc/models.py:314

Methodforward

(self, position, z, x, training=False, flags=None, debug=False)

douzero/dmc/models.py:371

Methodforward

(self, position, z, x, training=False, flags=None)

douzero/dmc/models.py:409

Methodget_model

(self, position)

douzero/dmc/models.py:390

Methodget_model

(self, position)

douzero/dmc/models.py:426

Methodget_models

(self)

douzero/dmc/models.py:393

Methodget_models

(self)

douzero/dmc/models.py:429

Functionget_move_type

(move)

douzero/env/move_detector.py:14

Functionmp_simulate

(card_play_data_list, card_play_model_path_dict, q, output, bid_output, title)

douzero/evaluation/simulation.py:25

Methodparameters

(self, position)

douzero/dmc/models.py:387

Methodparameters

(self, position)

douzero/dmc/models.py:423

douzero/dmc/models.py:375

Methodshare_memory

(self)

douzero/dmc/models.py:413

Methodstep

Step function takes as input the action, which is a list of integers, and output the next obervation, reward, and a Boolean v

douzero/env/env.py:228

Methodstep

(self, closure=None)

douzero/radam/radam.py:28

Methodstep

(self, closure=None)

douzero/radam/radam.py:116

Methodstep

(self, closure=None)

douzero/radam/radam.py:192

← previous101–168 of 168, ranked by callers