RobustInverseReinforcementLearningunder TransitionDynamicsMismatch

Leveraginginsights from theRobustRLliterature, wepropose arobustMCEIRLalgorithm, which is a principled approach to help with this mismatch. Finally, we empirically demonstrate the stable performance of our algorithm compared to the standard MCEIRL algorithm under transition dynamics mismatches in both finite and continuousMDPproblems.