Access the full text.
Sign up today, get DeepDyve free for 14 days.
Holger Prothmann, F. Rochner, Sven Tomforde, J. Branke, C. Müller-Schloer, H. Schmeck (2008)
Organic Control of Traffic Lights
A. Bazzan (2004)
A Distributed Approach for Coordination of Traffic Signal AgentsAutonomous Agents and Multi-Agent Systems, 10
ACM Transactions on Autonomous and Adaptive Systems
Francisco Melo, M. Veloso (2009)
Learning of coordination: exploiting sparse interactions in multiagent systems
M. Littman, N. Ravi, E. Fenson, R. Howard (2004)
Reinforcement learning for autonomic network repairInternational Conference on Autonomic Computing, 2004. Proceedings.
Bruno Silva, Eduardo Basso, A. Bazzan, P. Engel (2006)
Dealing with non-stationary environments using context detectionProceedings of the 23rd international conference on Machine learning
G. Tesauro, D. Chess, W. Walsh, R. Das, A. Segal, Ian Whalley, J. Kephart, Steve White (2004)
A multi-agent systems approach to autonomic computingProceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004.
J. Schneider, Weng-Keen Wong, A. Moore, Martin Riedmiller (1999)
Distributed Value Functions
P. Montague (2005)
Reinforcement Learning: An IntroductionIEEE Transactions on Neural Networks
J. Dowling, R. Cunningham, T. Walsh, Donal erty, A. Nedos, J. Andersson, M. Haahr, Marco Kilijan, Kulpreet Singh, Vinny Reynolds, E. Baniassad, S. Dobson, S. Farrell, A. Harrington, S. Clarke, C. Jensen, R. McGuinness, P. Barron, G. Biegel, S. Weber, R. Meier, D. Dahlem, Ivana Dusparic (2005)
The Decentralised Coordination of Self-Adaptive Components for Autonomic Distributed Systems
C. Watkins, P. Dayan (2004)
Technical Note: Q-LearningMachine Learning, 8
Ivana Dusparic, V. Cahill (2009)
Using Reinforcement Learning for Multi-policy Optimization in Decentralized Autonomic Systems - An Experimental Evaluation
As'ad Salkham, V. Cahill (2010)
Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning13th International IEEE Conference on Intelligent Transportation Systems
Silvia Richter (2006)
Learning Road Traffic Control: Towards Practical Traffic Control Using Policy Gradients
Autonomic Multi-Policy Optimization in Pervasive Systems: Overview and
Julien Perez, C. Germain, B. Kégl, C. Loomis (2008)
Grid Differentiated Services: A Reinforcement Learning Approach2008 Eighth IEEE International Symposium on Cluster Computing and the Grid (CCGRID)
G. Tesauro, Nicholas Jong, R. Das, M. Bennani (2006)
A Hybrid Reinforcement Learning Approach to Autonomic Resource Allocation2006 IEEE International Conference on Autonomic Computing
H. Cuayáhuitl, S. Renals, Oliver Lemon, H. Shimodaira (2006)
Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces
Carlos Guestrin, M. Lagoudakis, Ronald Parr (2002)
Coordinated Reinforcement Learning
Vinny Reynolds, V. Cahill, A. Senart (2006)
Requirements for an ubiquitous computing simulation and emulation environment
J. Kephart, D. Chess (2003)
The Vision of Autonomic ComputingComputer, 36
B. Abdulhai, R. Pringle, G. Karakoulas (2003)
Reinforcement learning for true adaptive traffic signal controlJournal of Transportation Engineering-asce, 129
S. Taylor (1999)
MAKING WAY FOR EMERGENCY VEHICLES
As'ad Salkham, R. Cunningham, Anurag Garg, V. Cahill (2008)
A Collaborative Reinforcement Learning Approach to Urban Traffic Control Optimization2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2
Shivaram Kalyanakrishnan, P. Stone (2007)
Batch reinforcement learning in a complex domain
J. Kok, P. Hoen, B. Bakker, N. Vlassis (2005)
Utile Coordination: Learning Interdependencies Among Cooperative Agents
Gerhard Weiss (1999)
Multiagent Systems
M. Humphreys (1997)
Action selection methods using reinforcement learning
Ivana Dusparic, V. Cahill (2009)
Distributed W-Learning: Multi-Policy Optimization in Self-Organizing Systems2009 Third IEEE International Conference on Self-Adaptive and Self-Organizing Systems
J. Dowling, R. Cunningham, E. Curran, V. Cahill (2006)
Building autonomic systems using collaborative reinforcement learningThe Knowledge Engineering Review, 21
G. Tesauro, R. Das, W. Walsh, J. Kephart (2005)
Utility-Function-Driven Resource Allocation in Autonomic SystemsSecond International Conference on Autonomic Computing (ICAC'05)
Ricardo Hoar, Joanne Penner, C. Jacob (2002)
Evolutionary swarm traffic: if ant roads had traffic lightsProceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600), 2
Ming Tan (1997)
Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents
Zhao-sheng Yang, Xin Chen, Yang Tang, Jianping Sun (2005)
Intelligent cooperation control of urban traffic networks2005 International Conference on Machine Learning and Cybernetics, 3
Andrea Omicini, A. Poggi (2006)
Multiagent SystemsIntelligenza Artificiale, 3
A. Febbraro, D. Giglio, N. Sacco (2004)
Urban traffic control structure based on hybrid Petri netsIEEE Transactions on Intelligent Transportation Systems, 5
B. Scholkopf, J. Platt, T. Hofmann (2007)
Natural Actor-Critic for Road Traffic Optimisation
D. Bernstein, S. Zilberstein, N. Immerman (2000)
The Complexity of Decentralized Control of Markov Decision ProcessesArXiv, abs/1301.3836
Richard Sutton, A. Barto (1998)
Introduction to Reinforcement Learning
G. Tesauro (2007)
Reinforcement Learning in Autonomic Computing: A Manifesto and Case StudiesIEEE Internet Computing, 11
Marco Wiering, J. Veenen, J. Vreeken, A. Koopman (2004)
Intelligent Traffic Light Control
Autonomic Multi-Policy Optimization in Pervasive Systems: Overview and Evaluation IVANA DUSPARIC and VINNY CAHILL, Trinity College Dublin This article describes Distributed W-Learning (DWL), a reinforcement learning-based algorithm for collaborative agent-based optimization of pervasive systems. DWL supports optimization towards multiple heterogeneous policies and addresses the challenges arising from the heterogeneity of the agents that are charged with implementing them. DWL learns and exploits the dependencies between agents and between policies to improve overall system performance. Instead of always executing the locally-best action, agents learn how their actions affect their immediate neighbors and execute actions suggested by neighboring agents if their importance exceeds the local action s importance when scaled using a prede ned or learned collaboration coef cient. We have evaluated DWL in a simulation of an Urban Traf c Control (UTC) system, a canonical example of the large-scale pervasive systems that we are addressing. We show that DWL outperforms widely deployed xed-time and simple adaptive UTC controllers under a variety of traf c loads and patterns. Our results also con rm that enabling collaboration between agents is bene cial as is the ability for agents to learn the degree to which it is appropriate for them to collaborate.
ACM Transactions on Autonomous and Adaptive Systems (TAAS) – Association for Computing Machinery
Published: Apr 1, 2012
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.