robo-dopamine-rl

【设计与创意】Overcome reward function design challenges via General Reward Model (GRM) for step-wise progress assessment. Uses multi-view observations for occlusion robustness, hop-based progress normalization, Policy-Invariant Reward Shaping—enabling 95% robot task success within 150 interactions with theoretically-grounded dense rewards.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准