Safe Offline Reinforcement Learning with Real-Time Budget Constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929263424307200 |
|---|---|
| author | Lin, Qian Tang, Bo Wu, Zifan Yu, Chao Mao, Shangqin Xie, Qianlong Wang, Xingxing Wang, Dong |
| author_facet | Lin, Qian Tang, Bo Wu, Zifan Yu, Chao Mao, Shangqin Xie, Qianlong Wang, Xingxing Wang, Dong |
| contents | Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years. However, most existing works in the literature still focus on the online setting where risky violations of the safety budget are likely to be incurred during training. Besides, in many real-world applications, the learned policy is required to respond to dynamically determined safety budgets (i.e., constraint threshold) in real time. In this paper, we target at the above real-time budget constraint problem under the offline setting, and propose Trajectory-based REal-time Budget Inference (TREBI) as a novel solution that models this problem from the perspective of trajectory distribution and solves it through diffusion model planning. Theoretically, we prove an error bound of the estimation on the episodic reward and cost under the offline setting and thus provide a performance guarantee for TREBI. Empirical results on a wide range of simulation tasks and a real-world large-scale advertising application demonstrate the capability of TREBI in solving real-time budget constraint problems under offline settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_00603 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Safe Offline Reinforcement Learning with Real-Time Budget Constraints Lin, Qian Tang, Bo Wu, Zifan Yu, Chao Mao, Shangqin Xie, Qianlong Wang, Xingxing Wang, Dong Machine Learning Artificial Intelligence Robotics Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years. However, most existing works in the literature still focus on the online setting where risky violations of the safety budget are likely to be incurred during training. Besides, in many real-world applications, the learned policy is required to respond to dynamically determined safety budgets (i.e., constraint threshold) in real time. In this paper, we target at the above real-time budget constraint problem under the offline setting, and propose Trajectory-based REal-time Budget Inference (TREBI) as a novel solution that models this problem from the perspective of trajectory distribution and solves it through diffusion model planning. Theoretically, we prove an error bound of the estimation on the episodic reward and cost under the offline setting and thus provide a performance guarantee for TREBI. Empirical results on a wide range of simulation tasks and a real-world large-scale advertising application demonstrate the capability of TREBI in solving real-time budget constraint problems under offline settings. |
| title | Safe Offline Reinforcement Learning with Real-Time Budget Constraints |
| topic | Machine Learning Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2306.00603 |