Abstract
The capacity to apply knowledge in a context different than the one in which it was learned has become crucial within the area of autonomous agents. This paper specifically addresses the issue of transfer of knowledge acquired through online learning in partially observable environments. We investigate the discovery of relevant abstract concepts which help the transfer of knowledge in the context of an environment characterized by its 2D geographical configuration. The architecture proposed is tested in a simple grid-world environment where two agents duel each other. Results show that an agent’s performances are improved through learning, including when it is tested on a map it has not yet seen.
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
Madeira, C., Corruble, V., Ramalho, G.: Designing a Reinforcement Learning-based Adaptive AI for Large-Scale Strategy Games. In: AIIDE (2006)
Ponsen, M., Munoz-Avila, H., Spronck, P., Aha, D.: Automatically Generating Game Tactics through Evolutionary Learning. AI Magazine (2006)
Leffler, B.R., Littman, M., Edmunds, T.: Efficient Reinforcement Learning With Relocatable Action Models. In: Proc. of AAAI (2007)
Driessens, K., Givan, R., Tadepalli, P.: RRL: An overview. In: Proc. of ICML (2004)
Guestrin, C., Koller, D., Gearhart, C., Kanodia, N.: Generalizing Plans to New Environments in Relational MDPs. In: IJCAI (2003)
Sharma, M., Holmes, M., Santamaria, J.C., Irani, A., Lee, C., Ram, I.J.A.: Transfer Learning in Real-Time Strategy Games using hybrid cbr/rl. In: IJCAI (2007)
Thrun, S., Pratt, L.: Learning to learn, Norwell edn. Kluwer Academic Publishers, Dordrecht (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Herpson, C., Corruble, V. (2009). Discovering Abstract Concepts to Aid Cross-Map Transfer for a Learning Agent. In: Gama, J., Costa, V.S., Jorge, A.M., Brazdil, P.B. (eds) Discovery Science. DS 2009. Lecture Notes in Computer Science(), vol 5808. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04747-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-04747-3_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04746-6
Online ISBN: 978-3-642-04747-3
eBook Packages: Computer ScienceComputer Science (R0)