Abstract
We identify a specialised class of reinforcement learning problem in which the agent(s) have the goal of gathering information (identifying the hidden state). The gathered information can affect rewards but not optimal behaviour. Exploiting this characteristic, an algorithm is developed for evaluating an agent’s policy against all possible hidden state histories at the same time. Experimental results show the method is effective in a two-dimensional multi-pursuer evader searching task. A comparison is made between identical policies, joint policies and “relational” policies that exploit relativistic information about the pursuers’ positions.
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
Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge (1998)
Thrun, S.: Monte carlo POMDPs. In: Solla, S., Leen, T., Müller, K. (eds.) Advances in Neural Information Processing Systems, vol. 12, pp. 1064–1070. MIT Press, Cambridge (2000)
Doucet, A., de Freitas, J.F.G. (eds.): N.J.G.: Sequential Monte Carlo Methods in Practice. Springer, New York (2001)
Roy, N., Gordon, G.: Exponential family PCA for belief compression in POMDPs. In: Advances in Neural Information Processing Systems (2002)
Strens, M.J.A., Moore, A.W.: Direct policy search using paired statistical tests. In: Proceedings of the 18th International Conference on Machine Learning, pp. 545–552. Morgan Kaufmann, San Francisco (2001)
Storn, R., Price, K.: Differential evolution - a simple and efficient adaptive scheme for global optimization over continuous spaces. Technical Report TR-95-012, International Computer Science Institute, Berkeley, CA (1995)
Strens, M.J.A., Moore, A.W.: Policy search using paired comparisons. Journal of Machine Learning Research 3, 921–950 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Strens, M.J.A. (2005). Learning Multi-agent Search Strategies. In: Kudenko, D., Kazakov, D., Alonso, E. (eds) Adaptive Agents and Multi-Agent Systems II. AAMAS AAMAS 2004 2003. Lecture Notes in Computer Science(), vol 3394. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-32274-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-32274-0_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25260-3
Online ISBN: 978-3-540-32274-0
eBook Packages: Computer ScienceComputer Science (R0)