Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.26478 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910257844846592 |
|---|---|
| author | You, Haoxiang Liu, Yilang Zong, Davis Wang, Qian Vitchutripop, Teeratham Wang, Qi Rakita, Daniel Abraham, Ian |
| author_facet | You, Haoxiang Liu, Yilang Zong, Davis Wang, Qian Vitchutripop, Teeratham Wang, Qi Rakita, Daniel Abraham, Ian |
| contents | We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end within a few hours on a single NVIDIA RTX 4080 GPU. SDPG estimates policy gradients via random perturbations of trajectory rollouts, requiring orders of magnitude fewer batch-rendered environments and substantially reducing compute and memory overhead. On visual MuJoCo benchmarks, SDPG consistently outperforms baseline methods in training time, memory usage, and rewards. Finally, to support future research, we introduce a suite of realistic visual robotics benchmarks spanning dexterous manipulation, challenging locomotion, and demonstrate effective sim-to-real transfer on physical hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26478 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient You, Haoxiang Liu, Yilang Zong, Davis Wang, Qian Vitchutripop, Teeratham Wang, Qi Rakita, Daniel Abraham, Ian Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Systems and Control We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end within a few hours on a single NVIDIA RTX 4080 GPU. SDPG estimates policy gradients via random perturbations of trajectory rollouts, requiring orders of magnitude fewer batch-rendered environments and substantially reducing compute and memory overhead. On visual MuJoCo benchmarks, SDPG consistently outperforms baseline methods in training time, memory usage, and rewards. Finally, to support future research, we introduce a suite of realistic visual robotics benchmarks spanning dexterous manipulation, challenging locomotion, and demonstrate effective sim-to-real transfer on physical hardware. |
| title | Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2605.26478 |