nip.trainers.malt_pure_text._PartialRolloutNode

class nip.trainers.malt_pure_text._PartialRolloutNode(current_env_state: ~nip.utils.nested_array_dict.NestedArrayDict, ended: bool = False, trajectory_env_states: list[~nip.utils.nested_array_dict.NestedArrayDict] = <factory>, node_id: int = -1, parent_partial_rollout: ~nip.trainers.malt_pure_text._PartialRolloutNode | None = None, child_partial_rollouts: list[~nip.trainers.malt_pure_text._PartialRolloutNode] = <factory>, num_branches: int = 0, total_reward_per_agent: ~numpy.ndarray | float = 0.0, node_id_base: dataclasses.InitVar[typing.Optional[int]] = None)

A node in the tree of responses, which is a partially generated rollout.

Methods Summary

__eq__(other)	Return self==value.
__init__(current_env_state[, ended, ...])
__post_init__(node_id_base)
__repr__()	Return repr(self).
clone_as_child()

Attributes

ended
node_id
node_id_base
num_branches
parent_partial_rollout
total_reward_per_agent
current_env_state
trajectory_env_states
child_partial_rollouts

Methods

__eq__(other)

Return self==value.

__init__(current_env_state: ~nip.utils.nested_array_dict.NestedArrayDict, ended: bool = False, trajectory_env_states: list[~nip.utils.nested_array_dict.NestedArrayDict] = <factory>, node_id: int = -1, parent_partial_rollout: ~nip.trainers.malt_pure_text._PartialRolloutNode | None = None, child_partial_rollouts: list[~nip.trainers.malt_pure_text._PartialRolloutNode] = <factory>, num_branches: int = 0, total_reward_per_agent: ~numpy.ndarray | float = 0.0, node_id_base: dataclasses.InitVar[typing.Optional[int]] = None) → None

__post_init__(node_id_base: int | None)

__repr__()

Return repr(self).

clone_as_child()