Thanks for tuning in to Google I/O. View all sessions on demandWatch on demand

tf_agents.trajectories.termination

Returns a TimeStep with step_type set to StepType.LAST.

tf_agents.trajectories.termination(
    observation: tf_agents.typing.types.NestedTensorOrArray,
    reward: tf_agents.typing.types.NestedTensorOrArray,
    outer_dims: Optional[types.Shape] = None
) -> tf_agents.trajectories.TimeStep

Used in the notebooks

Used in the tutorials

observation A NumPy array, tensor, or a nested dict, list or tuple of arrays or tensors.
reward A NumPy array, tensor, or a nested dict, list or tuple of arrays or tensors.
outer_dims (optional) If provided, it will be used to determine the batch dimensions. If not, the batch dimensions will be inferred by reward's shape.

A TimeStep.