AI RESEARCH

Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets

arXiv CS.LG

ArXi:2510.01479v2 Announce Type: replace Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contaminated by adversarial poisoning, system errors, or low-quality samples, leading to degraded policy performance in standard behavioral cloning (BC) and offline RL methods. This paper