- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
CRUCIBLE trains a high-level manipulation planner by replacing decisions in failed trajectories from saved simulator states and replaying the recorded suffix to identify repairable actions. The resulting counterfactual returns guide masked PPO updates, and the paper reports 62.38% success on tabletop grasping, compared with 56.44% for supervised fine-tuning and 55.45% for episode-return PPO.
Critical strengths
- Counterfactual replay provides more localized credit assignment than a single reward for the whole episode.
- The controlled comparison shows gains over both the SFT baseline and episode-return PPO.
Critical weaknesses
- The experimental design is somewhat confusing. My understanding is that the SFT used in Cosmos3 and RoboBrain 2.5 differs from the SFT proposed in this paper. It is also unclear whether the preceding component is a contribution of this paper.
- The proposed reinforcement learning training scheme appears to offer only limited gains over SFT alone, and its scope is quite narrow.
- Quantitative evaluation focuses on simulated tabletop grasping, while the hardware deployment is not evaluated with comparable success-rate results.
Questions for authors
I don’t think the main text needs to be packed with so many equations. More space should be devoted to the experiments, as the current experimental content and plans still seem rather limited.