Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2307.16348 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917577297494016 |
|---|---|
| author | White, Devin Wu, Mingkang Novoseller, Ellen Lawhern, Vernon J. Waytowich, Nicholas Cao, Yongcan |
| author_facet | White, Devin Wu, Mingkang Novoseller, Ellen Lawhern, Vernon J. Waytowich, Nicholas Cao, Yongcan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_16348 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Rating-based Reinforcement Learning White, Devin Wu, Mingkang Novoseller, Ellen Lawhern, Vernon J. Waytowich, Nicholas Cao, Yongcan Machine Learning Artificial Intelligence Robotics 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. |
| title | Rating-based Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2307.16348 |