Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.19548 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915257468846080 |
|---|---|
| author | Yuan, Mingqi Castanyer, Roger Creus Li, Bo Jin, Xin Zeng, Wenjun Berseth, Glen |
| author_facet | Yuan, Mingqi Castanyer, Roger Creus Li, Bo Jin, Xin Zeng, Wenjun Berseth, Glen |
| contents | Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and annotation. This limitation underscores the necessity for intrinsic rewards, which offer auxiliary and dense signals and can enable agents to learn in an unsupervised manner. Although various intrinsic reward formulations have been proposed, their implementation and optimization details are insufficiently explored and lack standardization, thereby hindering research progress. To address this gap, we introduce RLeXplore, a unified, highly modularized, and plug-and-play framework offering reliable implementations of eight state-of-the-art intrinsic reward methods. Furthermore, we conduct an in-depth study that identifies critical implementation details and establishes well-justified standard practices in intrinsically-motivated RL. Our documentation, examples, and source code are available at https://github.com/RLE-Foundation/RLeXplore. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19548 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning Yuan, Mingqi Castanyer, Roger Creus Li, Bo Jin, Xin Zeng, Wenjun Berseth, Glen Machine Learning Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and annotation. This limitation underscores the necessity for intrinsic rewards, which offer auxiliary and dense signals and can enable agents to learn in an unsupervised manner. Although various intrinsic reward formulations have been proposed, their implementation and optimization details are insufficiently explored and lack standardization, thereby hindering research progress. To address this gap, we introduce RLeXplore, a unified, highly modularized, and plug-and-play framework offering reliable implementations of eight state-of-the-art intrinsic reward methods. Furthermore, we conduct an in-depth study that identifies critical implementation details and establishes well-justified standard practices in intrinsically-motivated RL. Our documentation, examples, and source code are available at https://github.com/RLE-Foundation/RLeXplore. |
| title | RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.19548 |