Hamid R. Berenji, David Vengerov  Home/Search
Context Related
| stanford.edu/~venger...postIEEEpaper.ps stanford.edu/~vengero...fuzzIEEE00.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: stanford.edu/~vengerov/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: | This paper presents the rst results in understanding the reasons for cooperative advantage between reinforcement learning agents. We consider a cooperation method which consists of using and updating a common policy. We tested this method on a complex fuzzy reinforcement learning problem and found that cooperation brings larger than expected bene ts. More precisely, we found that K cooperative agents each learning for N time steps outperform K independent agents each learning in a separate... (Update)
BibTeX entry: (Update)
Berenji, Hamid R. and Vengerov, David (2000) "Advantages of Cooperation Between Reinforcement Learning Agents in Difficult Stochastic Problems." Accepted for publication in the 9th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE '00). Available electronically from http://www.stanford.edu/~vengerov. http://citeseer.ist.psu.edu/269628.html More
@misc{ hamid00advantages,
author = "B. Hamid and R. Vengerov",
title = "Advantages of Cooperation Between Reinforcement Learning Agents in Difficult
Stochastic Problems",
text = "Berenji, Hamid R. and Vengerov, David (2000) Advantages of Cooperation
Between Reinforcement Learning Agents in Difficult Stochastic Problems.
Accepted for publication in the 9th IEEE International Conference on Fuzzy
Systems (FUZZ-IEEE '00). Available electronically from http://www.stanford.edu/~vengerov.",
year = "2000",
url = "citeseer.ist.psu.edu/269628.html" }
Citations (may not include all citations):614 Reinforcement Learning: An Introduction - Sutton, Barto - 1998
413 NeuroDynamic Programming (context) - Bertsekas, Tsitsiklis - 1996
199 Markov Games as a Framework for Multi-agent Reinforcement Le.. - Littman - 1994
135 Multi-Agent Reinforcement Learning: Independent vs - Tan - 1993
99 Introducing the Tileworld: Experimentally Evaluating Agent A.. - Pollack, Ringuette - 1990
59 Feature-Based Methods for Large-Scale Dynamic Programming - Tsitsiklis, Van Roy - 1996
51 Reinforcement Learning in the Multi-Robot Domain - Mataric - 1997
44 Multiagent Systems - Sycara - 1998
43 A Complexity Analysis of Cooperative Mechanisms in Reinforce.. (context) - Whitehead - 1991
31 Opaque-Transition Reinforcement Learning (context) - Stone, Veloso - 1999
6 Foundations of Multi-Agent Systems: Issues and Directions (context) - Luck - 1997
5 Cooperation and Coordination Between Fuzzy Reinforcement Lea.. - Berenji, Vengerov - 1999
2 Increased Learning Rates Through the Sharing of Experiences .. (context) - Kelly, Keating - 1998
Documents on the same site (http://www.stanford.edu/~vengerov/): More
Gated Experts for Classification of Financial Time Series - Vengerov (1997) (Correct)
Optimal Control of Nonlinear Simultaneous Systems - Vengerov (1997) (Correct)
Stock Market Pattern Recognition with Neural Networks - Vengerov (1997) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC