Abstract
In the context of reinforcement learning, transfer learning refers to the concept of reusing knowledge acquired in past tasks to speed up the learning procedure in new tasks. Transfer learning methods have been succesfully applied in single-agent reinforcement learning algorithms, but no prior work has focused on applying them in a multi-agent environment. We propose a novel method for transfer learning in multi-agent reinforcement learning domains. We proceed to test the proposed approach in a multi-agent domain under various configurations. The results demonstrate that the method can reduce the learning time and increase the asymptotic performance of the learning algorithm.
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.
Similar content being viewed by others
References
Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: 15th National Conference on Artificial Intelligence, pp. 746–752 (1998)
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)
Hailu, G., Sommer, G.: On amount and quality of bias in reinforcement learning, vol. 2, pp. 728–733 (1999)
Kok, J.R., Vlassis, N.: The pursuit domain package. Technical report ias-uva-03-03, University of Amsterdam, The Netherlands (2003)
Konidaris, G., Barto, A.: Autonomous shaping: knowledge transfer in reinforcement learning. In: 23rd International Conference on Machine Learning, pp. 489–496 (2007)
Lazaric, A.: Knowledge Transfer in Reinforcement Learning. Ph.D. thesis, Politecnico di Milano (2008)
Madden, M.G., Howley, T.: Transfer of experience between reinforcement learning environments with progressive difficulty. Artificial Intelligence Review 21(3-4), 375–398 (2004)
Soni, V., Singh, S.: Using homomorphisms to transfer options across continuous reinforcement learning domains. In: AAAI Conference on Artificial Intelligence, pp. 494–499 (2006)
Taylor, M., Stone, P.: Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research 10, 1633–1685 (2009)
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 International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 283–290 (2008)
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)
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)
Weiss, G.: A Modern Approach to Distributed Artificial Intelligence. MIT Press (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Boutsioukis, G., Partalas, I., Vlahavas, I. (2012). Transfer Learning in Multi-Agent Reinforcement Learning Domains. In: Sanner, S., Hutter, M. (eds) Recent Advances in Reinforcement Learning. EWRL 2011. Lecture Notes in Computer Science(), vol 7188. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29946-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-29946-9_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29945-2
Online ISBN: 978-3-642-29946-9
eBook Packages: Computer ScienceComputer Science (R0)