tf_agents.bandits.policies.greedy_multi_objective_neural_policy.scalarize_objectives

Scalarize a rank-3 objectives tensor into a rank-2 tensor.

Scalarize an objective values tensor shaped as [batch_size, num_of_objectives, num_of_actions] along the second dimension into a rank-2 tensor shaped as [batch_size, num_of_actions]

objectives_tensor An objectives tensor to be scalarized.
scalarizer A tf_agents.bandits.multi_objective.multi_objective_scalarizer.Scalarizer object that implements scalarization of multiple objectives into a single scalar reward.

A rank-2 tensor of scalarized rewards shaped as [batch_size, num_of_actions].

ValueError If objectives_tensor is not rank-3.