Rollback: Experience Backtracking in World Models for Policy Improvement
Rollback leverages rewindable world models to improve robot policies by backtracking experience, enabling counterfactual exploration and outperforming baselines on real tasks.
ls ./papers | grep "#test-time physics grounding"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
1 paper · #test-time physics grounding
Rollback leverages rewindable world models to improve robot policies by backtracking experience, enabling counterfactual exploration and outperforming baselines on real tasks.