Rollback: Experience Backtracking in World Models for Policy Improvement
This work introduces Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines, and builds a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle.
Jia-Yi Luo, Yang Zhang, Li-Liang Chen et al.
· 0 citations