Language

unilab.base.np_env.NpEnvState¶

class unilab.base.np_env.NpEnvState[source]¶

Bases: object

NpEnvState(obs: ‘dict[str, np.ndarray]’, reward: ‘np.ndarray’, terminated: ‘np.ndarray’, truncated: ‘np.ndarray’, info: ‘dict[str, Any]’, final_observation: ‘dict[str, np.ndarray] | None’ = None)

Parameters:

obs (dict[str, ndarray])
reward (ndarray)
terminated (ndarray)
truncated (ndarray)
info (dict[str, Any])
final_observation (dict[str, ndarray] | None)

Methods

`__init__`(obs, reward, terminated, truncated, ...)
`replace`(**updates)

Attributes

`final_observation`
`obs`
`reward`
`terminated`
`truncated`
`info`

obs: dict[str, ndarray]¶

reward: ndarray¶

terminated: ndarray¶

truncated: ndarray¶

info: dict[str, Any]¶

final_observation: dict[str, ndarray] | None = None¶

replace(**updates)[source]¶

Parameters:: updates (Any)
Return type:: NpEnvState

__init__(obs, reward, terminated, truncated, info, final_observation=None)¶

Parameters:

obs (dict[str, ndarray])
reward (ndarray)
terminated (ndarray)
truncated (ndarray)
info (dict[str, Any])
final_observation (dict[str, ndarray] | None)