Multi-agent Learning Dynamics: A Survey Export

@incollection{citeulike:6032526, abstract = {In this paper we compare state-of-the-art multi-agent reinforcement learning algorithms in a wide variety of games. We consider two types of algorithms: value iteration and policy iteration. Four characteristics are studied: initial conditions, parameter settings, convergence speed, and local versus global convergence. Global convergence is still difficult to achieve in practice, despite existing theoretical guarantees. Multiple visualizations are included to provide a comprehensive insight into the learning dynamics.}, author = {van den Herik, H. and Hennes, D. and Kaisers, M. and Tuyls, K. and Verbeeck, K.}, booktitle = {Cooperative Information Agents XI}, citeulike-article-id = {6032526}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-75119-9_4}, citeulike-linkout-1 = {http://www.springerlink.com/content/dh25513561546332}, doi = {10.1007/978-3-540-75119-9_4}, issn = {1611-3349}, journal = {Cooperative Information Agents XI}, keywords = {2007, comparison, multi-agent, reinforcement-learning, simulation, survey}, month = {September}, pages = {36--56}, posted-at = {2009-10-29 16:06:07}, priority = {0}, publisher = {Springer Berlin / Heidelberg}, series = {Lecture Notes in Computer Science}, title = {Multi-agent Learning Dynamics: A Survey}, url = {http://dx.doi.org/10.1007/978-3-540-75119-9_4}, year = {2007} }

TY - CHAP ID - citeulike:6032526 L3 - citeulike-article-id:6032526 N2 - In this paper we compare state-of-the-art multi-agent reinforcement learning algorithms in a wide variety of games. We consider two types of algorithms: value iteration and policy iteration. Four characteristics are studied: initial conditions, parameter settings, convergence speed, and local versus global convergence. Global convergence is still difficult to achieve in practice, despite existing theoretical guarantees. Multiple visualizations are included to provide a comprehensive insight into the learning dynamics. JF - Cooperative Information Agents XI SE - Lecture Notes in Computer Science SN - 1611-3349 EP - 56 TI - Multi-agent Learning Dynamics: A Survey PB - Springer Berlin / Heidelberg T2 - Cooperative Information Agents XI SP - 36 KW - 2007 KW - comparison KW - multi-agent KW - reinforcement-learning KW - simulation KW - survey AU - van den Herik, H AU - Hennes, D AU - Kaisers, M AU - Tuyls, K AU - Verbeeck, K PY - 2007/09// UR - http://dx.doi.org/10.1007/978-3-540-75119-9_4 ER -