Rating-based Reinforcement Learning

Devin White, Mingkang Wu, Ellen Novoseller, Vernon Lawhern, Nicholas R Waytowich, Yongcan Cao

Keywords: Learning from human feedback, Reinforcement learning, Human ratings

TL;DR: This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning.

Abstract: This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning. Different from the existing preference-based and ranking-based reinforcement learning paradigms, based on human relative preferences over sample pairs, the proposed rating-based reinforcement learning approach is based on human evaluation of individual trajectories without relative comparisons between sample pairs. The rating-based reinforcement learning approach builds on a new prediction model for human ratings and a novel multi-class loss function. We conduct several experimental studies based on synthetic ratings and real human ratings to evaluate the effectiveness and benefits of the new rating-based reinforcement learning approach.

Submission Number: 40