Featured

Rollback: Using World-Model Backtracking of Counterfactual Experience to Improve Robot Policies

Rollback proposes a policy improvement paradigm that turns an action-conditioned world model from a one-way simulator into a backtrackable counterfactual engine: it returns to key decision points, branches to try different actions, and compares the outcomes, thereby distilling counterfactual results into action-level supervision without learning a separate value model.

This page provides a summary and source link only.