tf_agents.replay_buffers.reverb_utils.ReverbTrajectorySequenceObserver

Reverb trajectory sequence observer.

Inherits From: ReverbAddTrajectoryObserver

tf_agents.replay_buffers.reverb_utils.ReverbTrajectorySequenceObserver(
    py_client: tf_agents.typing.types.ReverbClient,
    table_name: Union[Text, Sequence[Text]],
    sequence_length: int,
    stride_length: int = 1,
    priority: Union[float, int] = 1
)

This is equivalent to ReverbAddTrajectoryObserver but sequences are not cut when a boundary trajectory is seen. This allows for sequences to be sampled with boundaries anywhere in the sequence rather than just at the end.

Consider using this observer when you want to create training experience that can encompass any subsequence of the observed trajectories.

Note: Counting of steps in drivers does not include boundary steps. To guarantee only 1 item is pushed to the replay when collecting n steps with a sequence_length of n make sure to set the stride_length

Args
py_client	Python client for the reverb replay server.
table_name	The table name(s) where samples will be written to.
sequence_length	The sequence_length used to write to the given table.
stride_length	The integer stride for the sliding window for overlapping sequences. The default value of 1 creates an item for every window. Using L = sequence_length this means items are created for times {0, 1, .., L-1}, {1, 2, .., L}, .... In contrast, stride_length = L will create an item only for disjoint windows {0, 1, ..., L-1}, {L, ..., 2 * L - 1}, ....
priority	Initial priority for new samples in the RB.

Methods

close

View source

close()

Closes the writer of the observer.

Note: Using the observer after closing it is not supported.

open

View source

open()

Open the writer of the observer.

reset

View source

reset()

Resets the state of the observer.

No data observed before the reset will be pushed to the RB.

__call__

View source

__call__(
    trajectory
)

Writes the trajectory into the underlying replay buffer.

Allows trajectory to be a flattened trajectory. No batch dimension allowed.

Args
trajectory	The trajectory to be written which could be (possibly nested) trajectory object or a flattened version of a trajectory. It assumes there is no batch dimension.