Back to Results
First PageMeta Content
Learning / Science / Dynamic programming / Markov processes / Stochastic control / Reinforcement learning / Q-learning / Agent-based model / Markov decision process / Statistics / Machine learning / Behaviorism


Dynamic Potential-Based Reward Shaping Sam Devlin Daniel Kudenko Department of Computer Science,
Add to Reading List

Document Date: 2012-05-08 10:32:01

Open Document

File Size: 290,94 KB

Share Result on Facebook

City

dynamic potential / Valencia / New York / /

Company

John Wiley & Sons Inc. / Artificial Neural Networks / MIT Press / ICANN / Multiagent Systems / /

Country

United States / Spain / /

/

Facility

University of York / University of Illinois / University of Massachusetts / /

IndustryTerm

reinforcement learning algorithm / reinforcement learning algorithms / multi-agent systems / Online learning / unshaped and shaped systems / /

Organization

University of Illinois / University of York / UK Department of Computer Science / MIT / Dynamic Potential-Based Reward Shaping Sam Devlin Daniel Kudenko Department of Computer Science / University of Massachusetts / Amherst / International Foundation for Autonomous Agents / /

Person

Sam Devlin Daniel Kudenko / Ai / Stochastic Game / /

Position

General / additional reward representative / /

ProvinceOrState

Illinois / New York / Massachusetts / /

PublishedMedium

Machine Learning / Complex Systems / Journal of Artificial Intelligence Research / /

Technology

reinforcement learning algorithms / artificial intelligence / Machine learning / reinforcement learning algorithm / Q-learning algorithm / /

URL

www.ifaamas.org / /

SocialTag