Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

15

IAT
2008
IEEE

favoriteEmaildiscussreport

161views Intelligent Agents» more IAT 2008»

Scaling Up Multi-agent Reinforcement Learning in Complex Domains

13 years 4 months ago

Scaling Up Multi-agent Reinforcement Learning in Complex Domains

Download www3.ntu.edu.sg

TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neighboring-agent mechanism, to further improve the learning efficiency of TD-FALCON in complex multi-agent domains. Through experiments on a traffic control problem domain and the herding task, we demonstrate that those strategies enable TD-FALCON to remain functional and adaptable in complex multi-agent domains.

Dan Xiao, Ah-Hwee Tan

Real-time Traffic

Complex Multi-agent Domains | Fusion Architecture | IAT 2008 | Intelligent Agents | Temporal Difference |

claim paper

Related Content

» The Self Organization of Context for Learning in MultiAgent Games

» Cooperative MultiAgent Learning The State of the Art

» Bayesian reinforcement learning for POMDPbased dialogue systems

» Adaptive Retrieval Agents Internalizing Local Context and Scaling up to the Web

» Scaling ModelBased AverageReward Reinforcement Learning for Product Delivery

» Generalized model learning for reinforcement learning in factored domains

» Using ILP to Improve Planning in Hierarchical Reinforcement Learning

» Integrating organizational control into multiagent learning

» Adaptive Blocking Learning to Scale Up Record Linkage

Post Info
More Details (n/a)

Added	08 Dec 2010
Updated	08 Dec 2010
Type	Conference
Year	2008
Where	IAT
Authors	Dan Xiao, Ah-Hwee Tan

Comments (0)