Inverse Delayed Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915047695974400 |
|---|---|
| author | Zhan, Simon Sinong Wu, Qingyuan Ruan, Zhian Yang, Frank Wang, Philip Wang, Yixuan Jiao, Ruochen Huang, Chao Zhu, Qi |
| author_facet | Zhan, Simon Sinong Wu, Qingyuan Ruan, Zhian Yang, Frank Wang, Philip Wang, Yixuan Jiao, Ruochen Huang, Chao Zhu, Qi |
| contents | Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed disturbances. Instead of relying on direct observations, our approach employs an efficient off-policy adversarial training framework to derive expert features and recover optimal policies from augmented delayed observations. Empirical evaluations in the MuJoCo environment under diverse delay settings validate the effectiveness of our method. Furthermore, we provide a theoretical analysis showing that recovering expert policies from augmented delayed observations outperforms using direct delayed observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02931 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Inverse Delayed Reinforcement Learning Zhan, Simon Sinong Wu, Qingyuan Ruan, Zhian Yang, Frank Wang, Philip Wang, Yixuan Jiao, Ruochen Huang, Chao Zhu, Qi Machine Learning Artificial Intelligence Systems and Control Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed disturbances. Instead of relying on direct observations, our approach employs an efficient off-policy adversarial training framework to derive expert features and recover optimal policies from augmented delayed observations. Empirical evaluations in the MuJoCo environment under diverse delay settings validate the effectiveness of our method. Furthermore, we provide a theoretical analysis showing that recovering expert policies from augmented delayed observations outperforms using direct delayed observations. |
| title | Inverse Delayed Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2412.02931 |