Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
World-Gymnast: Training Robots with Reinforcement Learning in a World Model
Ansh Kumar Sharma, Yixiang Sun, Ninghao Lu +3
Robot learning from interacting with the physical world is fundamentally bottlenecked by the cost of physical interaction. The two alternatives, supervised finetuning (SFT) from ex…
cs.RO2025
WorldGym: World Model as An Environment for Policy Evaluation
Julian Quevedo, Ansh Kumar Sharma, Yixiang Sun +3
Evaluating robot control policies is difficult: real-world testing is costly, and handcrafted simulators require manual effort to improve in realism and generality. We propose a wo…