Transfer Learning Heuristically Accelerated Algorithm: A Case Study with Real Robots

Abstract

Reinforcement Learning (RL) is a successful technique for learning the solutions of control problems from an agent's interaction in its domain. However, RL is known to be inefficient for real-world applications. In this paper we propose to use a combination of case-based reasoning (CBR) and heuristically accelerated reinforcement learning methods aiming to speed up a Reinforcement Learning algorithm in a transfer learning problem. We show results of applying this method on a robot soccer domain, where the use of the proposed method led to a significant improvement in the learning rate.