ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
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_ | 1866915170862759936 |
|---|---|
| author | Zhang, Chen Bo Calvin Hong, Zhang-Wei Pacchiano, Aldo Agrawal, Pulkit |
| author_facet | Zhang, Chen Bo Calvin Hong, Zhang-Wei Pacchiano, Aldo Agrawal, Pulkit |
| contents | Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computationally efficient manner remains an open challenge. We propose Online Reward Selection and Policy Optimization (ORSO), a novel approach that frames the selection of shaping reward function as an online model selection problem. ORSO automatically identifies performant shaping reward functions without human intervention with provable regret guarantees. We demonstrate ORSO's effectiveness across various continuous control tasks. Compared to prior approaches, ORSO significantly reduces the amount of data required to evaluate a shaping reward function, resulting in superior data efficiency and a significant reduction in computational time (up to 8 times). ORSO consistently identifies high-quality reward functions outperforming prior methods by more than 50% and on average identifies policies as performant as the ones learned using manually engineered reward functions by domain experts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13837 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization Zhang, Chen Bo Calvin Hong, Zhang-Wei Pacchiano, Aldo Agrawal, Pulkit Machine Learning Artificial Intelligence Robotics Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computationally efficient manner remains an open challenge. We propose Online Reward Selection and Policy Optimization (ORSO), a novel approach that frames the selection of shaping reward function as an online model selection problem. ORSO automatically identifies performant shaping reward functions without human intervention with provable regret guarantees. We demonstrate ORSO's effectiveness across various continuous control tasks. Compared to prior approaches, ORSO significantly reduces the amount of data required to evaluate a shaping reward function, resulting in superior data efficiency and a significant reduction in computational time (up to 8 times). ORSO consistently identifies high-quality reward functions outperforming prior methods by more than 50% and on average identifies policies as performant as the ones learned using manually engineered reward functions by domain experts. |
| title | ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization |
| topic | Machine Learning Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2410.13837 |