Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910578236194816 |
|---|---|
| author | Cutler, Elizabeth Xing, Yuning Cui, Tony Zhou, Brendan van Rijnsoever, Koen Hart, Ben Valencia, David Ong, Lee Violet C. Gee, Trevor Liarokapis, Minas Williams, Henry |
| author_facet | Cutler, Elizabeth Xing, Yuning Cui, Tony Zhou, Brendan van Rijnsoever, Koen Hart, Ben Valencia, David Ong, Lee Violet C. Gee, Trevor Liarokapis, Minas Williams, Henry |
| contents | Reinforcement Learning (RL) training is predominantly conducted in cost-effective and controlled simulation environments. However, the transfer of these trained models to real-world tasks often presents unavoidable challenges. This research explores the direct training of RL algorithms in controlled yet realistic real-world settings for the execution of dexterous manipulation. The benchmarking results of three RL algorithms trained on intricate in-hand manipulation tasks within practical real-world contexts are presented. Our study not only demonstrates the practicality of RL training in authentic real-world scenarios, facilitating direct real-world applications, but also provides insights into the associated challenges and considerations. Additionally, our experiences with the employed experimental methods are shared, with the aim of empowering and engaging fellow researchers and practitioners in this dynamic field of robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14747 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper Cutler, Elizabeth Xing, Yuning Cui, Tony Zhou, Brendan van Rijnsoever, Koen Hart, Ben Valencia, David Ong, Lee Violet C. Gee, Trevor Liarokapis, Minas Williams, Henry Robotics Artificial Intelligence Machine Learning Reinforcement Learning (RL) training is predominantly conducted in cost-effective and controlled simulation environments. However, the transfer of these trained models to real-world tasks often presents unavoidable challenges. This research explores the direct training of RL algorithms in controlled yet realistic real-world settings for the execution of dexterous manipulation. The benchmarking results of three RL algorithms trained on intricate in-hand manipulation tasks within practical real-world contexts are presented. Our study not only demonstrates the practicality of RL training in authentic real-world scenarios, facilitating direct real-world applications, but also provides insights into the associated challenges and considerations. Additionally, our experiences with the employed experimental methods are shared, with the aim of empowering and engaging fellow researchers and practitioners in this dynamic field of robotics. |
| title | Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2408.14747 |