arXiv subjects

Riki Eto

Publications and source records attributed to Riki Eto.

2 recordsLinked to original sources

arXiv2023

A proof of convergence of inverse reinforcement learning for multi-objective optimization

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.

cs.LG↗

arXiv2023

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

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.

cs.LG↗