3 papers
cs.RO2026
GAINS: Leveraging Inconsistent Human Intervention Signals in Reinforcement Learning
Xinyi Zhang, Yinuo Zhao, Pei Ren +7
Correcting robot manipulation policies through human intervention holds great promise for real-world deployment, yet human operators are inherently imperfect in both the actions th…
cs.LG2026
Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Hao Wang, Hao Gu, Hongming Piao +6
The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while…
cs.RO2025
Real-world Reinforcement Learning from Suboptimal Interventions
Yinuo Zhao, Huiqian Jin, Lechun Jiang +9
Real-world reinforcement learning (RL) offers a promising approach to training precise and dexterous robotic manipulation policies in an online manner, enabling robots to learn fro…