All learning is local: Multi-agent learning in global reward games Yu-Han Chang MIT CSAIL Cambridge, MA 02139 - Han learning - Document - PDFSEARCH.IO

First Page	Meta Content
	All learning is local: Multi-agent learning in global reward games Yu-Han Chang MIT CSAIL Cambridge, MA 02139 Add to Reading List Document Date: 2004-07-01 07:47:52 Open Document File Size: 1,29 MB Share Result on Facebook Company MIT Press / / / Event Diplomatic Relations / / IndustryTerm 4x4 adhoc-networking domain / ad-hoc networking / cooperative multiaent systems / good learning algorithms / mobilized ad-hoc networks / mobile ad-hoc networking domain / linear systems / e-mdps / / Organization MIT / National Aeronautics and Space Administration / American Society of Mechanical Engineers / / Person Andras Lorincz / Daishi Harada / Andrew G. Barto / Balimt Takacs / Tracey Ho / Stuart Russell / Andrew Y. Ng / Istvan Szita / Leslie Pack Kaelbling / Craig Boutilier / Richard S. Sutton / Caroline Claus / / / Position teacher / rT / personal coach / / ProvinceOrState Massachusetts / / PublishedMedium Journal of Machine Learning Research / / Technology ordinary Q-learning algorithm / artificial intelligence / Machine Learning / tabular Q-learning algorithm / good learning algorithms / Q-learning algorithm / / SocialTag Markov processes Stochastic control Robot control Reinforcement learning Q-learning Markov decision process Kalman filter Multi-armed bandit Machine learning Statistics

All learning is local: Multi-agent learning in global reward games Yu-Han Chang MIT CSAIL Cambridge, MA 02139Add to Reading List