src.plangym.videogames.retro#

Implement the plangym API for retro environments.

Classes#

`ActionDiscretizer`	Wrap a gym-retro environment and make it use discrete actions for the Sonic game.
`RetroEnv`	Environment for playing `gym-retro` games.

Module Contents#

class src.plangym.videogames.retro.ActionDiscretizer(env, actions=None)[source]#

Bases: gymnasium.ActionWrapper

Wrap a gym-retro environment and make it use discrete actions for the Sonic game.

buttons = ['B', 'A', 'MODE', 'START', 'UP', 'DOWN', 'LEFT', 'RIGHT', 'C', 'Y', 'X', 'Z']#

actions#

_actions = []#

action_space#: Return the Env action_space unless overwritten then the wrapper action_space is used.

action(a)[source]#

Return the corresponding action in the emulator’s format.

Return type:: int

class src.plangym.videogames.retro.RetroEnv(name, frameskip=5, episodic_life=False, autoreset=True, delay_setup=False, remove_time_limit=True, obs_type='rgb', render_mode=None, wrappers=None, **kwargs)[source]#

Bases: plangym.videogames.env.VideogameEnv

Environment for playing gym-retro games.

Parameters:

name (str)
frameskip (int)
episodic_life (bool)
autoreset (bool)
delay_setup (bool)
remove_time_limit (bool)
obs_type (str)
render_mode (str | None)
wrappers (Iterable[plangym.core.wrap_callable] | None)

AVAILABLE_OBS_TYPES#

SINGLETON = True#

__getattr__(item)[source]#: Forward getattr to self.gym_env.

static get_win_condition(info)[source]#

Get win condition for games that have the end of the screen available.

Parameters:: info (dict[str, Any])
Return type:: bool

get_ram()[source]#

Return the ram of the emulator as a numpy array.

Return type:: numpy.ndarray

clone(**kwargs)[source]#

Return a copy of the environment with its initialization delayed.

Return type:: RetroEnv

init_gym_env()[source]#

Initialize the retro environment.

Return type:: gymnasium.Env

get_state()[source]#

Get the state of the retro environment.

Return type:: numpy.ndarray

set_state(state)[source]#

Set the state of the retro environment.

Parameters:: state (numpy.ndarray)

close()[source]#: Close the underlying gym.Env.

reset(return_state=True)[source]#

Restart the environment.

Parameters:: return_state (bool) – If True, it will return the state of the environment.
Returns:: (state, obs) if `return_state is True else return obs.
Return type:: numpy.ndarray | tuple[numpy.ndarray, numpy.ndarray]