Module: tf_agents.policies.greedy_policy

Policy implementation that generates greedy actions from another policy.

Classes

class DeterministicWithLogProb: Thin wrapper around Deterministic that supports taking log_prob.

class GreedyPolicy: Returns greedy samples of a given policy.

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.