tf_agents.agents.ppo.ppo_utils.make_trajectory_mask
Mask boundary trajectories and those with invalid returns and advantages.
tf_agents.agents.ppo.ppo_utils.make_trajectory_mask(
batched_traj: tf_agents.trajectories.Trajectory
) -> tf_agents.typing.types.Tensor
Args |
batched_traj
|
Trajectory, doubly-batched [batch_dim, time_dim,...]. It must
be preprocessed already.
|
Returns |
A mask, type tf.float32, that is 0.0 for all between-episode Trajectory
(batched_traj.step_type is LAST) and 0.0 if the return value is
unavailable.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[]]