Xin Liu, Yixuan Li, Yuhui Chen, Yuxing Qin, Haoran Li, Dongbin Zhao

Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL

arXiv:2602.12636v1 Announce Type: new Abstract: Designing suitable rewards poses a significant challenge in reinforcement learning (RL), especially for embodied manipulation. Trajectory success rewards are suitable …