An Autonomous Transfer Learning Algorithm for TD-Learners
The main objective of transfer learning is to use the knowledge acquired from a source task in order to boost the learning procedure in a target task. Transfer learning comprises a suitable solution for reinforcement learning algorithms, which often require a considerable amount of training time, especially when dealing with complex tasks. This work proposes an autonomous method for transfer learning in reinforcement learning agents. The proposed method is empirically evaluated in the keepaway and the mountain car domains. The results demonstrate that the proposed method can improve the learning procedure in the target task.
Unable to display preview. Download preview PDF.
- 3.Sutton, R.S., Barto, A.G.: Reinforcement Learning, An Introduction. MIT Press (1998)Google Scholar
- 7.Taylor, M.E., Kuhlmann, G., Stone, P.: Autonomous transfer for reinforcement learning. In: 7th AAMAS, pp. 283–290 (2008)Google Scholar
- 9.Fernández, F., Veloso, M.: Probabilistic policy reuse in a reinforcement learning agent. In: 5th International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 720–727 (2006)Google Scholar
- 10.Taylor, M.E., Stone, P.: Cross-domain transfer for reinforcement learning. In: 24th International Conference on Machine Learning, pp. 879–886 (2007)Google Scholar
- 12.Talvitie, E., Singh, S.: An experts algorithm for transfer learning. In: 20th IJCAI, pp. 1065–1070 (2007)Google Scholar
- 13.Sorg, J., Singh, S.: Transfer via soft homomorphisms. In: Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2009, vol. 2, pp. 741–748 (2009)Google Scholar
- 14.Ammar, H.B., Tuyls, K., Taylor, M.E., Driessen, K., Weiss, G.: Reinforcement learning transfer via sparse coding. In: International Conference on Autonomous Agents and Multiagent Systems, AAMAS (June 2012)Google Scholar