Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912263188774912 |
|---|---|
| author | Labiosa, Adam Wang, Zhihan Agarwal, Siddhant Cong, William Hemkumar, Geethika Harish, Abhinav Narayan Hong, Benjamin Kelle, Josh Li, Chen Li, Yuhao Shao, Zisen Stone, Peter Hanna, Josiah P. |
| author_facet | Labiosa, Adam Wang, Zhihan Agarwal, Siddhant Cong, William Hemkumar, Geethika Harish, Abhinav Narayan Hong, Benjamin Kelle, Josh Li, Chen Li, Yuhao Shao, Zisen Stone, Peter Hanna, Josiah P. |
| contents | Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic selection. Our architecture led to victory in the 2024 RoboCup SPL Challenge Shield Division. In this work, we fully describe our system's architecture and empirically analyze key design decisions that contributed to its success. Our approach demonstrates how RL-based behaviors can be integrated into complete robot behavior architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09417 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer Labiosa, Adam Wang, Zhihan Agarwal, Siddhant Cong, William Hemkumar, Geethika Harish, Abhinav Narayan Hong, Benjamin Kelle, Josh Li, Chen Li, Yuhao Shao, Zisen Stone, Peter Hanna, Josiah P. Robotics Artificial Intelligence Machine Learning Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic selection. Our architecture led to victory in the 2024 RoboCup SPL Challenge Shield Division. In this work, we fully describe our system's architecture and empirically analyze key design decisions that contributed to its success. Our approach demonstrates how RL-based behaviors can be integrated into complete robot behavior architectures. |
| title | Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.09417 |