unilab.base.final_observation¶
Functions
|
Patch transition next obs with final_observation without mutating actor inputs. |
|
Resolve terminal observation facts without constructing patched next obs. |
|
Resolve actor/storage observations and timeout bootstrap masks for a step. |
Classes
TerminalObservationContract(terminal_obs: 'np.ndarray | None', terminal_mask: 'np.ndarray', timeout_terminal_mask: 'np.ndarray', terminal_critic: 'np.ndarray | None' = None) |
|
TransitionBootstrapContract(actor_next_obs: 'np.ndarray', transition_next_obs: 'np.ndarray', terminal_mask: 'np.ndarray', timeout_terminal_mask: 'np.ndarray', actor_next_critic: 'np.ndarray | None' = None, transition_next_critic: 'np.ndarray | None' = None) |
- class unilab.base.final_observation.TransitionBootstrapContract[source]¶
Bases:
objectTransitionBootstrapContract(actor_next_obs: ‘np.ndarray’, transition_next_obs: ‘np.ndarray’, terminal_mask: ‘np.ndarray’, timeout_terminal_mask: ‘np.ndarray’, actor_next_critic: ‘np.ndarray | None’ = None, transition_next_critic: ‘np.ndarray | None’ = None)
- Parameters:
- __init__(actor_next_obs, transition_next_obs, terminal_mask, timeout_terminal_mask, actor_next_critic=None, transition_next_critic=None)¶
- class unilab.base.final_observation.TerminalObservationContract[source]¶
Bases:
objectTerminalObservationContract(terminal_obs: ‘np.ndarray | None’, terminal_mask: ‘np.ndarray’, timeout_terminal_mask: ‘np.ndarray’, terminal_critic: ‘np.ndarray | None’ = None)
- Parameters:
- unilab.base.final_observation.patch_transition_next_obs(next_obs, final_observation=None, done=None, info=None, next_critic=None)[source]¶
Patch transition next obs with final_observation without mutating actor inputs.
- unilab.base.final_observation.resolve_transition_bootstrap_contract(next_obs, info=None, final_observation=None, done=None, truncated=None, next_critic=None)[source]¶
Resolve actor/storage observations and timeout bootstrap masks for a step.