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.

翻译：我们证明了在多目标优化中，Wasserstein逆强化学习能够使学习者的奖励值在有限迭代内模仿专家的奖励值。此外，我们还证明了，对于具有字典序的多目标优化，Wasserstein逆强化学习能够使学习者的最优解模仿专家的最优解。