Agent-Based System with Learning Capabilities for Transport Problems

In this paper we propose an agent architecture with learning capabilities and its application to a transportation problem. The agent consists of the several modules (control, execution, communication, task evaluation, planning and social) and knowledge bases to store information and learned knowledge. The proposed solution is tested on the PDPTW. Agents using supervised and reinforcement learning algorithms generate knowledge to evaluate arriving requests. Experimental results show that learning increases agent performance.

[1]  Jan D. Gehrke,et al.  Combining Rule Induction and Reinforcement Learning: An Agent-based Vehicle Routing , 2010, 2010 Ninth International Conference on Machine Learning and Applications.

[2]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[3]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[4]  Toshiharu Sugawara,et al.  On-Line Learning of Coordination Plans , 1993 .

[5]  Winfried Hochstättler,et al.  The Simulated Trading Heuristic for Solving Vehicle Routing Problems , 1996, Discret. Appl. Math..

[6]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[7]  Jacek Malec,et al.  Learning to evaluate conditional partial plans , 2007, ICMLA 2007.

[8]  Reid G. Smith,et al.  The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver , 1980, IEEE Transactions on Computers.

[9]  Bartlomiej Sniezynski,et al.  International Conference on Computational Science, ICCS 2011 Farmer-Pest Problem: A Multidimensional Problem Domain for Comparison of Agent Learning Methods , 2011, ICCS.

[10]  Sean Luke,et al.  Cooperative Multi-Agent Learning: The State of the Art , 2005, Autonomous Agents and Multi-Agent Systems.

[11]  Abder Koukam,et al.  Multi-agent Approach to Dynamic Pick-up and Delivery Problem with Uncertain Knowledge about Future Transport Demands , 2006, Fundam. Informaticae.

[12]  Jaroslaw Kozlak,et al.  Learning in Cooperating Agents Environment as a Method of Solving Transport Problems and Limiting the Effects of Crisis Situations , 2007, International Conference on Computational Science.

[13]  Julio Cesar Nievola,et al.  Statistical and Biological Validation Methods in Cluster Analysis of Gene Expression , 2007, ICMLA 2007.

[14]  Jörg P. Müller,et al.  COOPERATIVE TRANSPORTATION SCHEDULING : AN APPLICATION DOMAIN FOR DAI , 1996 .

[15]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[16]  Marco Aldinucci,et al.  Computational Science - ICCS 2008, 8th International Conference, Kraków, Poland, June 23-25, 2008, Proceedings, Part I , 2008, ICCS.

[17]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[18]  David Meignan,et al.  A Coalition-Based Metaheuristic for the vehicle routing problem , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[19]  Jan D. Gehrke,et al.  Traffic Prediction for Agent Route Planning , 2008, ICCS.

[20]  Jack Dongarra,et al.  Computational Science - ICCS 2007, 7th International Conference, Beijing, China, May 27 - 30, 2007, Proceedings, Part III , 2007, ICCS.