AI RESEARCH

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

arXiv CS.LG

ArXi:2512.02486v2 Announce Type: replace Single-domain offline reinforcement learning (RL) often suffers from limited data coverage, while cross-domain offline RL handles this issue by leveraging additional data from other domains with dynamics shifts. However, existing studies primarily focus on train-time robustness (handling dynamics shifts from