TaRL: Learning General and Physical Rewards from Tactile Demonstrations
This study addresses the limitation of visual rewards in capturing local physical interactions during contact-rich tasks, which leads to inefficient and brittle reinforcement learning. To overcome this, we propose a tactile reward learning framework that leverages tactile deformation maps to regress task progress, extracting generalizable physical feedback signals from both successful and failed demonstrations. By integrating visuotactile multimodal rewards for policy optimization, our approach transcends the constraints of purely visual observations. Experiments demonstrate that the proposed framework significantly improves sample efficiency and generalization across scene layouts and object instances, achieving strong performance in both simulated and real-world tasks. Notably, success rates increase from 34% to 56% for nut threading and from 37% to 97% for cube grasping.