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)[source]#

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)[source]#
__repr__()#

Return repr(self).

clone_as_child()[source]#