Article

Multi-Objective Reinforcement Learning with Routed Ensembles and Trajectory Attribution

This paper studies policy learning in multi-objective reinforcement learning, proposing objective-conflict coefficients and using them to derive near-optimal regret bounds for online settings, quantifying the impact of objective misalignment on learning efficiency. The authors design a routed ensemble policy learning algorithm that maintains a small set of basis policies and dynamically routes trajectories to the policy with the highest potential reward; they also propose a kernel surrogate trajectory attribution algorithm that estimates how trajectory feedback signals affect the policy learning of other trajectories.

Part of the event: Multi-Objective Reinforcement Learning Routing Ensemble and Trajectory Attribution Method

This page provides a summary and source link only.