A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimization

Abstract

We prove Wasserstein inverse reinforcement learning enables the learner's reward values to imitate the expert's reward values in a finite iteration for multi-objective optimizations. Moreover, we prove Wasserstein inverse reinforcement learning enables the learner's optimal solutions to imitate the expert's optimal solutions for multi-objective optimizations with lexicographic order.

9 pages. This text is continuation from arXiv:2305.06137