Learning device, learning method, and learning program

Abstract

A reward function estimation unitestimates a reward function by multiple importance sampling using samples of a decision-making history of a subject and of a decision-making history generated based on a sampling policy. A policy estimation unitestimates a policy by reinforcement learning using the estimated reward function. The reward function estimation unitsets the policy estimated by the policy estimation unit as a new sampling policy, and estimates the reward function by the multiple importance sampling using the samples of the decision-making history of the subject and of the decision-making history generated based on the sampling policy.