We show the convergence of Wasserstein inverse reinforcement learning for multi-objective optimizations with the projective subgradient method by formulating an inverse problem of the multi-objective optimization problem. In addition, we prove convergence of inverse reinforcement learning (maximum entropy inverse reinforcement learning, guided cost learning) with gradient descent and the projective subgradient method.

翻译：我们通过构建多目标优化问题的逆问题，证明了采用投影次梯度法的Wasserstein逆强化学习在多目标优化中的收敛性。此外，我们证明了基于梯度下降和投影次梯度法的逆强化学习（最大熵逆强化学习、引导代价学习）的收敛性。