2025-12-30: ✨ Codes, Dataset and Weights are coming soon! Stay tuned for updates.2025-12-30: 🔥 We released our Project Page of Robo-Dopamine.
- Release the 3B Dopamine-Reward (GRM) model and inference codes (About 2 week).
- Release the 8B Dopamine-Reward (GRM) model (About 2 week).
- Release the Robo-Dopamine Dataset and SFT training code (About 1 months).
- Release the Dataset Generation Pipeline (Maybe 1 months or more).
- Release the Dopamine-RL training code for simulator and real-world settings (Maybe 2 months or more).
Robo-Dopamine is composed of two core components: (a) Dopamine-Reward Modeling Method -- At the heart of our reward modeling is to build the General Reward Model (GRM), a vision-language model that is prompted with a task description and conditioned on multi-view images of initial, goal, "BEFORE," and "AFTER" states to predict a relative progress or regress hop. To ensure a stable and accurate signal, we employ Multi-Perspective Progress Fusion, which combines incremental, forward-anchored, and backward-anchored predictions into a final fused reward. And (b) Dopamine-RL Training Framework -- The Dopamine-RL framework first adapts the pre-trained GRM to a novel task using a single demonstration, i.e., One-Shot GRM Adaptation. Subsequently, it uses a theoretically-sound Policy-Invariant Reward Shaping method to convert the GRM's dense output into a reward signal that accelerates learning without altering the optimal policy. This approach is universally compatible with a wide range of RL algorithms.
If you find our work helpful, feel free to cite it:
@article{tan2025robo,
title={Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation},
author={Tan, Huajie and Chen, Sixiang and Xu, Yijie and Wang, Zixiao and Ji, Yuheng and Chi, Cheng and Lyu, Yaoxu and Zhao, Zhongxia and Chen, Xiansheng and Co, Peterson and others},
journal={arXiv preprint arXiv:2512.23703},
year={2025}
}