Multiagent reinforcement learning in Markov games : asymmetric and symmetric approaches

Modern computing systems are distributed, large and heterogeneous. Computers, other devices and humans are very tightly connected with each other and therefore it would be more preferable to handle these entities more as agents as stand-alone systems. One goal of the artificial intelligence is to understand interactions between entities, whether they are artificial or natural, and how to make good decisions taking other decision makers also into account. In this research project, these interactions between intelligent and rational agents are modeled with Markov games and the emphasis is on the adaptation and learning in multiagent systems.

[1]  Ville Könönen,et al.  Gradient Based Method for Symmetric and Asymmetric Multiagent Reinforcement Learning , 2003, IDEAL.

[2]  E. Oja,et al.  Asymmetric multiagent reinforcement learning in pricing applications , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[3]  Hybrid model for multiagent reinforcement learning , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[4]  Ville Könönen,et al.  Hybrid model for multiagent reinforcement learning , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[5]  Ville Könönen,et al.  Asymmetric multiagent reinforcement learning , 2003, Web Intell. Agent Syst..

[6]  Ville Könönen,et al.  Policy Gradient Method for Team Markov Games , 2004, IDEAL.