An online multi-agent co-operative learning algorithm in POMDPs

Authors: Liu, Fei; Zeng, Guangzhou

Source: Journal of Experimental & Theoretical Artificial Intelligence, Volume 20, Number 4, December 2008 , pp. 335-344(10)

Publisher: Taylor and Francis Ltd

Buy & download fulltext article:

Price: $56.94 plus tax (Refund Policy)

Abstract:

Solving partially observable Markov decision processes (POMDPs) is a complex task that is often intractable. This paper examines the problem of finding an optimal policy for POMDPs. While a lot of effort has been made to develop algorithms to solve POMDPs, the question of automatically finding good low-dimensional spaces in multi-agent co-operative learning domains has not been explored thoroughly. To identify this question, an online algorithm CMEAS is presented to improve the POMDP model. This algorithm is based on a look-ahead search to find the best action to execute at each cycle. Thus the overwhelming complexity of computing a policy for each possible situation is avoided. A series of simulations demonstrate this good strategy and performance of the proposed algorithm when multiple agents co-operate to find an optimal policy for POMDPs.

Keywords: online algorithm; multi-agent; co-operative learning; POMDPs

Document Type: Research article

DOI: http://dx.doi.org/10.1080/09528130701679820

Affiliations: 1: School of Computer Science and Technology, Shandong University, Jinan, People's Republic of China

Publication date: 2008-12-01

More about this publication?