Graduate studies at Western
|Abstract||This paper addresses automatic partitioning in complex reinforcement learning tasks with multiple agents, without a priori domain knowledge regarding task structures. Partitioning a state/input space into multiple regions helps to exploit the di erential characteristics of regions and di erential characteristics of agents, thus facilitating learning and reducing the complexity of agents especially when function approximators are used. We develop a method for optimizing the partitioning of the space through experience without the use of a priori domain knowledge. The method is experimentally tested and compared to a number of other algorithms. As expected, we found that the multi-agent method with automatic partitioning outperformed single-agent learning.|
|Keywords||No keywords specified (fix it)|
No categories specified
(categorize this paper)
|Through your library||Only published papers are available at libraries|
Similar books and articles
Karl Tuyls, Ann Nowe, Tom Lenaerts & Bernard Manderick (2004). An Evolutionary Game Theoretic Perspective on Learning in Multi-Agent Systems. Synthese 139 (2):297 - 330.
John Cantwell (2007). A Model for Updates in a Multi-Agent Setting. Journal of Applied Non-Classical Logics 17 (2):183-196.
Roland Mühlenbernd (2011). Learning with Neighbours. Synthese 183 (S1):87-109.
Ron Sun, Todd Peterson & Edward Merrill, Bottom-Up Skill Learning in Reactive Sequential Decision Tasks.
Ron Sun (2001). Cognitive Science Meets Multi-Agent Systems: A Prolegomenon. Philosophical Psychology 14 (1):5 – 28.
Sorry, there are not enough data points to plot this chart.
Added to index2010-12-22
Total downloads1 ( #292,081 of 739,318 )
Recent downloads (6 months)1 ( #61,243 of 739,318 )
How can I increase my downloads?