AI RESEARCH
Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
arXiv CS.LG
•
ArXi:2603.28281v1 Announce Type: new We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensional binary label vector representing each of the $n$ agents' preferences), an $\epsilon$-fraction of the samples may be arbitrarily corrupted. We model the problem using the framework of linear Marko games.