Online reinforcement learning (RL) enables robot policies to improve through physical interaction, but the assistance they require changes as their competence evolves. Existing intervention strategies based on offline estimates or fixed decision rules can therefore become mismatched to the current policy. To address th...
Yu-Dong Lin, Hao-Yuan Deng, Zhuo-Xuan Yuan et al.· 0 citations
Online reinforcement learning (RL) enables robots to continuously improve through real-world interaction, yet achieving high success rates in contact-rich manipulation remains challenging due to sparse binary rewards. Conventional reward-shaping methods rely on hand-designed goal-proximity heuristics and seldom differe...
Wen Guo, Pei-Zhi Tang, Yu-Kun Bai et al.· IEEE Robotics and Automation...· 1 citation
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system compone...
Facet-0 unifies multimodal representation learning and reinforcement learning post-training around a joint action-wrench proposal, which reaches 82% mean success on five sub-millimeter computer-assembly tasks, compared with 15% for the strongest baseline.
Hao-Yuan Deng, Hai-Chao Liu, Wen-Kai Guo et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.