DexPolicy：面向轨迹引导灵巧操作的调度式探索策略
DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation
DexPolicy 将强化学习的探索尺度设为训练步数的显式函数，从宽到窄退火，在 ViViDex 轨迹引导的灵巧操作任务中提升成功率。在五个 YCB 物体、三个随机种子上，FPO 的平均确定性 Target 成功率从 49.4% 升至 68.1%，GRPO 从 14.1% 升至 45.4%，PPO 从 32.0% 升至 35.7%。
Published on Sep 30
Authors:
,
,
,
,
,
Abstract
Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise that serves the first goal can interfere with the second. In trajectory-guided settings such as ViViDex, where RL refine hand-object trajectories from human video, our baseline PPO runs end near their initial action noise after 5M steps, motivating explicit control of exploration scale. DexPolicy makes that scale an explicit function of training steps, annealing from broad to narrow exploration while holding loss, architecture, reward, and optimizer settings fixed. We study three policy-optimization settings: PPO, critic-free GRPO continuation, and a flow-parameterized PPO variant (FPO). Across five YCB objects and three training seeds, mean deterministic Target success rises from 49.4% to 68.1% (FPO), 14.1% to 45.4% (GRPO), and 32.0% to 35.7% (PPO). On a RealMan RM75 arm with an Inspire/RH56 hand, 360 trials over three objects raise mean Target success from 25.0% to 85.0% (FPO), 10.0% to 63.3% (GRPO), and 8.3% to 43.3% (PPO), with one trained model per object-method condition. PPO component screening favors noise control over the tested optimizer contraction; the selected PPO schedule yields higher mean Target success than linear decay with the same endpoints on three tested objects. Training return, deterministic Target success, and tolerance to execution noise dissociate; schedules should therefore be judged by terminal task success under the intended execution conditions, per task and policy-optimization setting. Code: https://github.com/AIGeeksGroup/DexPolicy. Website: https://aigeeksgroup.github.io/DexPolicy.
View arXiv page View PDF Project page GitHub 0 Add to collection
Get this paper in your agent:
hf papers read 2610.00360
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.00360 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.00360 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.00360 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源：HuggingFace Daily Papers（社区热门论文） · huggingface.co