tf_agents.trajectories.Trajectory

A tuple that represents a trajectory.

View aliases

Main aliases

tf_agents.trajectories.trajectory.Trajectory

tf_agents.trajectories.Trajectory(
    step_type,
    observation,
    action,
    policy_info,
    next_step_type,
    reward,
    discount
)

Used in the notebooks

Used in the tutorials
Tutorial on Multi Armed Bandits in TF-Agents Tutorial on Ranking in TF-Agents

A Trajectory represents a sequence of aligned time steps. It captures the observation, step_type from current time step with the computed action and policy_info. Discount, reward and next_step_type come from the next time step.

Attributes
step_type	A StepType.
observation	An array (tensor), or a nested dict, list or tuple of arrays (tensors) that represents the observation.
action	An array/a tensor, or a nested dict, list or tuple of actions. This represents action generated according to the observation.
policy_info	An arbitrary nest that contains auxiliary information related to the action. Note that this does not include the policy/RNN state which was used to generate the action.
next_step_type	The StepType of the next time step.
reward	An array/a tensor, or a nested dict, list, or tuple of rewards. This represents the rewards and/or constraint satisfiability after performing the action in an environment.
discount	A scalar that representing the discount factor to multiply with future rewards.

Methods

is_boundary

View source

is_boundary() -> tf_agents.typing.types.Bool

is_first

View source

is_first() -> tf_agents.typing.types.Bool

is_last

View source

is_last() -> tf_agents.typing.types.Bool

is_mid

View source

is_mid() -> tf_agents.typing.types.Bool

replace

View source

replace(
    **kwargs
) -> 'Trajectory'

Exposes as namedtuple._replace.

Usage:

  new_trajectory = trajectory.replace(policy_info=())

This returns a new trajectory with an empty policy_info.

Args
**kwargs	key/value pairs of fields in the trajectory.

Returns
A new Trajectory.