Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Taylor, M.E., Stone, P., Liu, Y.: Transfer learning via inter-task mappings for temporal difference learning. Journal of Machine Learning Research 8, 2125–2167 (2007)
Fachantidis, A., Partalas, I., Taylor, M.E., Vlahavas, I.: Transfer learning via multiple inter-task mappings. In: Sanner, S., Hutter, M. (eds.) EWRL 2011. LNCS, vol. 7188, pp. 225–236. Springer, Heidelberg (2012)
Sutton, R.S., Barto, A.G.: Reinforcement Learning, An Introduction. MIT Press (1998)
Stone, P., Sutton, R.S., Kuhlmann, G.: Reinforcement learning for RoboCup-soccer keepaway. Adaptive Behavior 13(3), 165–188 (2005)
Singh, S.P., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. Machine Learning 22(1-3), 123–158 (1996)
Taylor, M.E., Jong, N.K., Stone, P.: Transferring instances for model-based reinforcement learning. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008, Part II. LNCS (LNAI), vol. 5212, pp. 488–505. Springer, Heidelberg (2008)
Taylor, M.E., Kuhlmann, G., Stone, P.: Autonomous transfer for reinforcement learning. In: 7th AAMAS, pp. 283–290 (2008)
Stone, P., Kuhlmann, G., Taylor, M.E., Liu, Y.: Keepaway soccer: From machine learning testbed to benchmark. In: Bredenfeld, A., Jacoff, A., Noda, I., Takahashi, Y. (eds.) RoboCup 2005. LNCS (LNAI), vol. 4020, pp. 93–105. Springer, Heidelberg (2006)
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)
Taylor, M.E., Stone, P.: Cross-domain transfer for reinforcement learning. In: 24th International Conference on Machine Learning, pp. 879–886 (2007)
Torrey, L., Shavlik, J., Walker, T., Maclin, R.: Skill acquisition via transfer learning and advice taking. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 425–436. Springer, Heidelberg (2006)
Talvitie, E., Singh, S.: An experts algorithm for transfer learning. In: 20th IJCAI, pp. 1065–1070 (2007)
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)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Fachantidis, A., Partalas, I., Taylor, M.E., Vlahavas, I. (2014). An Autonomous Transfer Learning Algorithm for TD-Learners. In: Likas, A., Blekas, K., Kalles, D. (eds) Artificial Intelligence: Methods and Applications. SETN 2014. Lecture Notes in Computer Science(), vol 8445. Springer, Cham. https://doi.org/10.1007/978-3-319-07064-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-07064-3_5
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07063-6
Online ISBN: 978-3-319-07064-3
eBook Packages: Computer ScienceComputer Science (R0)