No-Regret Learning and a Mechanism for Distributed Multiagent Planning Jan-P. Calliess Geoffrey J. Gordon

First Page		Document Content
Date: 2008-02-18 10:33:25 Loss function Reinforcement learning Forcing Price of anarchy Game theory Statistics Mechanism design		No-Regret Learning and a Mechanism for Distributed Multiagent Planning Jan-P. Calliess Geoffrey J. Gordon Add to Reading List Source URL: www.cs.cmu.edu Download Document from Source Website File Size: 207,86 KB Share Document on Facebook