Module: tf_agents.bandits.policies.greedy_multi_objective_neural_policy

Policy for greedy multi-objective prediction.

Classes

class GreedyMultiObjectiveNeuralPolicy: Class to build GreedyMultiObjectiveNeuralPolicy objects.

Functions

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

Type Aliases

NestedBoundedTensorSpec: The central part of internal API.