Abstract—By applying the knowledge previously obtained by reinforcement learning to new tasks, transfer learning has been successful in achieving efficient learning, rather than re-learning knowledge about action policies from scratch. However, in the case of applying transfer learning to reinforcement learning, it is not easy to determine which and how much the obtained knowledge should be transferred. With this background, in this study, we propose a novel method that enables to decide the knowledge and to determine the ratio of transference by adopting sparse coding in transfer learning. The transferred knowledge is represented as a linear combination of the accumulated knowledge by means of sparse coding. In the experiments, we have adopted colored mazes as tasks and confirmed that our proposed method significantly improved in terms of jumpstart and of the reduction of the total learning cost, compared with normal Q-learning.

Index Terms—sparse coding, transfer learning, reinforcement learning, maze

Cite: Midori Saito and Ichiro Kobayashi, "A Study on Efficient Transfer Learning for Reinforcement Learning Using Sparse Coding," Jounal of Automation and Control Engineering, Vol. 4, No. 4, pp. 324-330, August, 2016. doi: 10.18178/joace.4.4.324-330