cs.LG, econ.EM, math.OC, stat.ML

Inverse Reinforcement Learning with Just Classification and a Few Regressions

arXiv:2509.21172v2 Announce Type: replace
Abstract: Inverse reinforcement learning (IRL) aims to infer rewards from observed behavior, but rewards are not identified from the policy alone: many reward–value pairs can rationalize the same actions. Mea…