Rating-Based Reinforcement Learning

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.

Authors

• Devin White University of Texas, San Antonio
• Mingkang Wu University of Texas, San Antonio
• Ellen Novoseller DEVCOM Army Research Laboratory
• Vernon J. Lawhern DEVCOM Army Research Laboratory
• Nicholas Waytowich DEVCOM Army Research Laboratory
• Yongcan Cao University of Texas, San Antonio

Keywords

• HAI: Human-in-the-loop Machine Learning
• HAI: Learning Human Values and Preferences