Module: tf_agents.bandits.policies.greedy_multi_objective_neural_policy

Policy for greedy multi-objective prediction.

Classes

class GreedyMultiObjectiveNeuralPolicy: Class to build GreedyMultiObjectiveNeuralPolicy objects.

scalarize_objectives(...): Scalarize a rank-3 objectives tensor into a rank-2 tensor.

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.