tf_agents.utils.common.compute_returns

Compute the return from each index in an episode.

tf_agents.utils.common.compute_returns(
    rewards: tf_agents.typing.types.Tensor,
    discounts: tf_agents.typing.types.Tensor,
    time_major: bool = False
)

Args
`rewards`	Tensor `[T]`, `[B, T]`, `[T, B]` of per-timestep reward.
`discounts`	Tensor `[T]`, `[B, T]`, `[T, B]` of per-timestep discount factor. Should be `0`. for final step of each episode.
`time_major`	Bool, when batched inputs setting it to `True`, inputs are expected to be time-major: `[T, B]` otherwise, batch-major: `[B, T]`.

Returns
Tensor of per-timestep cumulative returns.

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.

tf_agents.utils.common.compute_returns

Args

Returns