Transfer Method for Reinforcement Learning in Same Transition Model -- Quick Approach and Preferential Exploration

Abstract

We aim to accelerate learning processes in reinforcement learning by transfer learning. Its concept is that knowledge to solve similar tasks accelerates a learning process of a target task. We have proposed that the basic transfer method based on forbidden rule set that is a set of rules which cause to immediately failure of a target task. However, the basic method works poorly for the gSame Transition Model,h which has same state transition probability and different goal. In this article, we propose an effective transfer learning method in same transition model. In detail, it consists of two strategies: (1) approaching to the goal for the selected source task quickly, and (2) exploring states around the goal preferentially.