Transfer Learning in Multi-Agent Reinforcement Learning Domains
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.
KeywordsReinforcement Learn Multiagent System Transfer Learning Target Task Direct Learning
Unable to display preview. Download preview PDF.
- 1.Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: 15th National Conference on Artificial Intelligence, pp. 746–752 (1998)Google Scholar
- 2.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
- 3.Hailu, G., Sommer, G.: On amount and quality of bias in reinforcement learning, vol. 2, pp. 728–733 (1999)Google Scholar
- 4.Kok, J.R., Vlassis, N.: The pursuit domain package. Technical report ias-uva-03-03, University of Amsterdam, The Netherlands (2003)Google Scholar
- 5.Konidaris, G., Barto, A.: Autonomous shaping: knowledge transfer in reinforcement learning. In: 23rd International Conference on Machine Learning, pp. 489–496 (2007)Google Scholar
- 6.Lazaric, A.: Knowledge Transfer in Reinforcement Learning. Ph.D. thesis, Politecnico di Milano (2008)Google Scholar
- 8.Soni, V., Singh, S.: Using homomorphisms to transfer options across continuous reinforcement learning domains. In: AAAI Conference on Artificial Intelligence, pp. 494–499 (2006)Google Scholar
- 11.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)Google Scholar
- 14.Weiss, G.: A Modern Approach to Distributed Artificial Intelligence. MIT Press (1999)Google Scholar