Neuroevolution is a promising approach for constructing intelligent agents in many complex tasks such as games, robotics, and decision making. It is also well suited for evolving team behavior for many multiagent tasks. However, new challenges and opportunities emerge in such tasks, including facilitating cooperation through reward sharing and communication, accelerating evolution through social learning, and measuring how good the resulting solutions are. This paper reviews recent progress in these three areas, and suggests avenues for future work.

PDF

In J. Liu et al., editors, Advances in Computational Intelligence, LNCS 7311, 24-46, Berlin, Heidelberg:, 2012. Springer.

@incollection{miikkulainen:wcci12, title={Multiagent Learning through Neuroevolution}, author={Risto Miikkulainen and Eliana Feasley and Leif Johnson and Igor Karpov and Padmini Rajagopalan and Aditya Rawal and Wesley Tansey}, booktitle={Advances in Computational Intelligence}, volume={LNCS 7311}, editor={J. Liu et al.}, address={Berlin, Heidelberg:}, publisher={Springer}, pages={24-46}, url="http://nn.cs.utexas.edu/?miikkulainen:wcci12", year={2012} }