Rollback: Experience Backtracking in World Models for Policy Improvement
Paper • 2610.36068 • Published • 54
Zhaodong Yan
Anhforth
AI & ML interests
None yet
Recent Activity
upvoted a paper 11 days ago
Rollback: Experience Backtracking in World Models for Policy Improvement upvoted a paper 19 days ago
Learning from Fleet Experience: A Collective Learning Paradigm for Robots authored a paper almost 3 years ago
Language Models can be Logical SolversOrganizations
upvoted a paper 11 days ago