نسخة أولية وصول مفتوح
ORPG: Reconciling Multiple Reward Objectives through Objective-wise Policy Gradients
Multi-reward policy optimization requires a joint update that reflects both the learning signals and the intended relationships among objectives. We introduce Objective-wise Reconciled Policy Gradient (ORPG), which constructs a separate clipped policy objective for each reward and reconciles the resulting gradients int …