rlcard.envs¶

rlcard.envs.env¶

class rlcard.envs.env.Env(config)¶

Bases: object

The base Env class. For all the environments in RLCard, we should base on this class and implement as many functions as we can.

get_action_feature(action)¶

For some environments such as DouDizhu, we can have action features

Returns:: The action features
Return type:: (numpy.array)

get_payoffs()¶

Get the payoffs of players. Must be implemented in the child class.

Returns:: A list of payoffs for each player.
Return type:: (list)

Note: Must be implemented in the child class.

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)

get_player_id()¶

Get the current player id

Returns:: The id of the current player
Return type:: (int)

get_state(player_id)¶

Get the state given player id

Parameters:: player_id (int) – The player id
Returns:: The observed state of the player
Return type:: (numpy.array)

is_over()¶

Check whether the curent game is over

Returns:: True if current game is over
Return type:: (boolean)

reset()¶

Start a new game

Returns:

Tuple containing:

(numpy.array): The begining state of the game (int): The begining player

Return type:

(tuple)

run(is_training=False)¶

Run a complete game, either for evaluation or training RL agent.

Parameters:: is_training (boolean) – True if for training purpose.
Returns:: (list): A list of trajectories generated from the environment. (list): A list payoffs. Each entry corresponds to one player.
Return type:: (tuple) Tuple containing

Note: The trajectories are 3-dimension list. The first dimension is for different players.: The second dimension is for different transitions. The third dimension is for the contents of each transiton

seed(seed=None)¶

set_agents(agents)¶

Set the agents that will interact with the environment. This function must be called before run.

Parameters:: agents (list) – List of Agent classes

step(action, raw_action=False)¶

Step forward

Parameters:

action (int) – The action taken by the current player
raw_action (boolean) – True if the action is a raw action

Returns:

Tuple containing:

(dict): The next state (int): The ID of the next player

Return type:

(tuple)

step_back()¶

Take one step backward.

Returns:

Tuple containing:

(dict): The previous state (int): The ID of the previous player

Return type:

(tuple)

Note: Error will be raised if step back from the root node.

rlcard.envs.registration¶

class rlcard.envs.registration.EnvRegistry¶

Bases: object

Register an environment (game) by ID

make(env_id, config={'allow_step_back': False, 'seed': None})¶

Create and environment instance

Parameters:

env_id (string) – The name of the environment
config (dict) – A dictionary of the environment settings

register(env_id, entry_point)¶

Register an environment

Parameters:

env_id (string) – The name of the environent
entry_point (string) – A string the indicates the location of the envronment class

class rlcard.envs.registration.EnvSpec(env_id, entry_point=None)¶

Bases: object

A specification for a particular instance of the environment.

make(config={'allow_step_back': False, 'seed': None})¶

Instantiates an instance of the environment

Returns:: An instance of the environemnt config (dict): A dictionary of the environment settings
Return type:: env (Env)

rlcard.envs.registration.make(env_id, config={})¶

Create and environment instance

Parameters:

env_id (string) – The name of the environment
config (dict) – A dictionary of the environment settings
env_num (int) – The number of environments

rlcard.envs.registration.register(env_id, entry_point)¶

Register an environment

Parameters:

env_id (string) – The name of the environent
entry_point (string) – A string the indicates the location of the envronment class

rlcard.envs.blackjack¶

class rlcard.envs.blackjack.BlackjackEnv(config)¶

Bases: Env

Blackjack Environment

get_payoffs()¶

Get the payoff of a game

Returns:: list of payoffs
Return type:: payoffs (list)

rlcard.envs.blackjack.get_score(hand)¶

rlcard.envs.doudizhu¶

class rlcard.envs.doudizhu.DoudizhuEnv(config)¶

Bases: Env

Doudizhu Environment

get_action_feature(action)¶

For some environments such as DouDizhu, we can have action features

Returns:: The action features
Return type:: (numpy.array)

get_payoffs()¶

Get the payoffs of players. Must be implemented in the child class.

Returns:: a list of payoffs for each player
Return type:: payoffs (list)

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)

rlcard.envs.limitholdem¶

class rlcard.envs.limitholdem.LimitholdemEnv(config)¶

Bases: Env

Limitholdem Environment

get_payoffs()¶

Get the payoff of a game

Returns:: list of payoffs
Return type:: payoffs (list)

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)

rlcard.envs.gin_rummy¶

File name: envs/gin_rummy.py Author: William Hale Date created: 2/12/2020

class rlcard.envs.gin_rummy.GinRummyEnv(config)¶

Bases: Env

GinRummy Environment

get_payoffs()¶

Get the payoffs of players. Must be implemented in the child class.

Returns:: a list of payoffs for each player
Return type:: payoffs (list)

rlcard.envs.leducholdem¶

class rlcard.envs.leducholdem.LeducholdemEnv(config)¶

Bases: Env

Leduc Hold’em Environment

get_payoffs()¶

Get the payoff of a game

Returns:: list of payoffs
Return type:: payoffs (list)

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)

rlcard.envs.mahjong¶

class rlcard.envs.mahjong.MahjongEnv(config)¶

Bases: Env

Mahjong Environment

get_payoffs()¶

Get the payoffs of players. Must be implemented in the child class.

Returns:: a list of payoffs for each player
Return type:: payoffs (list)

rlcard.envs.nolimitholdem¶

class rlcard.envs.nolimitholdem.NolimitholdemEnv(config)¶

Bases: Env

Limitholdem Environment

get_payoffs()¶

Get the payoff of a game

Returns:: list of payoffs
Return type:: payoffs (list)

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)

rlcard.envs.bridge¶

File name: envs/bridge.py Author: William Hale Date created: 11/26/2021

class rlcard.envs.bridge.BridgeEnv(config)¶

Bases: Env

Bridge Environment

get_payoffs()¶

Get the payoffs of players.

Returns:: A list of payoffs for each player.
Return type:: (list)

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)

class rlcard.envs.bridge.BridgePayoffDelegate¶

Bases: object

get_payoffs(game: BridgeGame)¶

Get the payoffs of players. Must be implemented in the child class.

Returns:: A list of payoffs for each player.
Return type:: (list)

Note: Must be implemented in the child class.

class rlcard.envs.bridge.BridgeStateExtractor¶

Bases: object

extract_state(game: BridgeGame)¶

Extract useful information from state for RL. Must be implemented in the child class.

Parameters:: game (BridgeGame) – The game
Returns:: The extracted state
Return type:: (numpy.array)

static get_legal_actions(game: BridgeGame)¶

Get all legal actions for current state.

Returns:: A OrderedDict of legal actions’ id.
Return type:: (OrderedDict)

get_state_shape_size() → int¶

class rlcard.envs.bridge.DefaultBridgePayoffDelegate¶

Bases: BridgePayoffDelegate

get_payoffs(game: BridgeGame)¶

Get the payoffs of players.

Returns:: A list of payoffs for each player.
Return type:: (list)

class rlcard.envs.bridge.DefaultBridgeStateExtractor¶

Bases: BridgeStateExtractor

extract_state(game: BridgeGame)¶

Extract useful information from state for RL.

Parameters:: game (BridgeGame) – The game
Returns:: The extracted state
Return type:: (numpy.array)

get_state_shape_size() → int¶

rlcard.envs.uno¶

class rlcard.envs.uno.UnoEnv(config)¶

Bases: Env

get_payoffs()¶

Get the payoffs of players. Must be implemented in the child class.

Returns:: A list of payoffs for each player.
Return type:: (list)

Note: Must be implemented in the child class.

get_perfect_information()¶

Get the perfect information of the current state

Returns:: A dictionary of all the perfect information of the current state
Return type:: (dict)