Influence zones: A strategy to enhance reinforcement learning

Neurocomputing

Volumn 70, Issue 1-3, 2006, Pages 21-34

  Braga, Arthur Plínio de S ^a   Araújo, Aluízio F R ^b  

^a FEDERAL UNIVERSITY OF CEARÁ   (Brazil)

^b FEDERAL UNIVERSITY OF PERNAMBUCO   (Brazil)

Author keywords

Instantaneous topological map; Learning acceleration; Reinforcement learning; Self organizing map

Indexed keywords

ESTIMATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; SELF ORGANIZING MAPS; TOPOLOGY;

INSTANTANEOUS TOPOLOGICAL MAP; LEARNING ACCELERATION; REINFORCEMENT LEARNING; VALUE FUNCTION ESTIMATION;

DECISION MAKING;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; CONTROLLED STUDY; DECISION MAKING; INTERMETHOD COMPARISON; LEARNING; PERFORMANCE; PRIORITY JOURNAL; REINFORCEMENT;

EID: 33750404375     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.07.010     Document Type: Article

References (32)

1. Bellman R. Dynamic Programming (1957), Princeton University Press, Princeton, NJ
2. Bertsekas D.P., and Tsitsiklis J.N. Neuro-Dynamic Programming (1996), Athena Scientific, Belmont, MA
3. Braga A.P.S., and Araújo A.F.R. A topological reinforcement learning agent for navigation. Neural Comput. Appl. 12 3-4 (2003) 220-236
4. Fritzke B. A growing neural gas network learns topologies. Adv. Neural Inform. Process. Syst. 7 (1995) 625-632
5. Fritzke B. Unsupervised ontogenetic networks. In: Fiesler E., and Beale R. (Eds). Handbook of Neural Computation (1996), Institute of Physics Publishing and Oxford University Press
6. George P.L. Automatic Mesh Generation-Application to Finite Element Methods (1991), Wiley, New York
7. A. Großmann, Continual learning for mobile robots, Ph.D. thesis, School of Computer Science, The University of Birmingham, Birmingham, UK, 2001.
8. J. Jockusch, H. Ritter, An instantaneous topological mapping model for correlated stimuli. Proceedings of the IJCNN'99, 1999, pp. 445.
9. Kaelbling L.P., Littman M.L., and Moore A.W. Reinforcement learning: a survey. J. Artif. Intell. Res. 4 (1996) 237-285
10. Kalos M.H., and Whhitlock P.A. Monte Carlo Methods (1986), Wiley, New York
11. Kim M.Y., and Cho H. Three-dimensional map building for mobile robot navigation environments using a self-organizing neural network. J. Robot. Syst. 21 6 (2004) 323-343
12. Koenig S., and Simmons R.G. The effect of representation and knowledge on goal-directed exploration with reinforcement learning algorithms. Mach. Learn. 22 (1996) 227-250
13. Kohonen T. Self-Organization and Associative Memory (1984), Springer, Heidelberg
14. Martinetz T., and Schulten K. Topology representing networks. Neural Networks 7 3 (1994) 507-522
15. Mason R.L., Gunst R.F., and Hess J.L. Statistical Design and Analysis of Experiments (1989), Wiley, New York
16. R.A. McCallum, Using transitional proximity for faster reinforcement learning, Proceedings of the Ninth International Conference on Machine Learning, 1992, pp. 316-321.
17. Milán J., and del R. Rapid, safe, and incremental learning of navigation strategies. IEEE Trans. Syst., Man, Cybernet. 26 (1996) 408-420
18. Millán J., del R., Posenato D., and Dedieu E. Continuous-action Q-learning. Mach. Learn. 49 (2002) 247-265
19. Montgomery D.C. Design and Analysis of Experiments (1984), Wiley, New York
20. Moore A.W., and Atkeson C.G. Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn. 13 (1993) 103-130
21. Peng J., and Williams R.J. Incremental multi-step Q-learning. Mach. Learn. 22 (1996) 283-290
22. C.H.C. Ribeiro, Aspects of the behaviour of a learning agent in control tasks, Ph.D. thesis, Imperial College of Science, Technology and Medicine, University of London, 1998.
23. Ribeiro C.H.C. Reinforcement learning agents. Artif. Intell. Rev. 17 (2002) 223-250
24. Ritter H., Martinetz T., and Schulten K. Neural Computation and Self-Organizing Maps-An Introduction (1992), Addison-Wesley Publishing Company, Reading, MA
25. G.A. Rummery, Problem solving with reinforcement learning, Ph.D. thesis, Cambridge University, 1995.
26. Schefler W.C. Statistics-Concepts and Applications (1988), The Benjamin/Cummings Publishing Company, Inc.
27. Smith A.J. Applications of the self-organising map to reinforcement learning. Neural Networks 15 8-9 (2002) 1107-1124
28. Sutton R.S. Dyna, an integrated architecture for learning, planning, and reacting. SIGART Bull. 2 (1991) 160-163 ACM Press
29. Sutton R.S., and Barto A. Introduction to Reinforcement Learning (1998), MIT Press/Bradford Books, Cambridge, MA
30. Touzet C. Neural reinforcement learning for behaviour synthesis. Robot. Autonom. Syst. 22 3-4 (1997) 251-281
31. C.J.C.H. Watkins, Learning from delayed rewards, Ph.D. thesis, King's College, Cambridge, 1989.
32. Wiering M., and Schimidhuber J. Fast online Q(λ). Mach. Learn. 33 (1998) 105-115