Theoretical Considerations of Potential-Based Reward Shaping for Multi-Agent Systems Sam Devlin Daniel Kudenko - Reward system - Document - PDFSEARCH.IO - Document Search Engine

Back to Results

First Page	Meta Content
	Theoretical Considerations of Potential-Based Reward Shaping for Multi-Agent Systems Sam Devlin Daniel Kudenko Add to Reading List Document Date: 2012-05-08 10:32:01 Open Document File Size: 380,43 KB Share Result on Facebook City Taipei / New York / Cambridge / London / / Company Neural Information Processing Systems / LG / MIT Press / MultiAgent Systems / Wireless Sensor Networks / AAAI Press / John Wiley & Sons Inc. / Wellman / John Wiley and Sons / / Country Taiwan / United States / / Facility UK University of York / University of Massachusetts / Multi-Agent Systems Sam Devlin Daniel Kudenko University of York / / IndustryTerm reinforcement learning solutions / reinforcement learning solution / cooperative multi-agent systems / reinforcement learning algorithm / reinforcement learning algorithms / multi-agent systems / temporal difference algorithms / heterogeneous cooperative multi-agent systems / multi-agent reinforcement learning solution / multi-agent specific algorithms / information processing systems / joint action learning algorithms / multi-agent reinforcement applications / learning algorithm / learning algorithms / / Organization University of York / MIT / University of Massachusetts / Amherst / International Foundation for Autonomous Agents / Department of Computer Science / NASA Ames Research Center / / Person Daniel Kudenko / C.Poskitt / Sam Devlin / Ai / Stochastic Game / Nash Equilibrium / Nash Q-learning / C. Eric Wiewiora / Nash Equilibria / / Position joint policy representative / General / designer / / ProvinceOrState New York / Massachusetts / / PublishedMedium Machine Learning / Journal of Artificial Intelligence Research / Complex Systems / The Journal of Machine Learning Research / / Technology existing reinforcement learning algorithms / Machine Learning / Qlearning algorithm / multi-agent specific algorithms / learning algorithm / reinforcement learning algorithms / artificial intelligence / temporal difference algorithms / learning algorithms / joint action learning algorithms / reinforcement learning algorithm / Q-learning algorithm / / URL www.ifaamas.org / / SocialTag Artificial intelligence Behavior Reinforcement learning Q-learning Game theory SARSA Temporal difference learning Agent-based model Multi-agent system Statistics