Multi-agent reinforcement learning: Weighting and partitioning

Neural Networks

Volumn 12, Issue 4-5, 1999, Pages 727-753

  Sun, R ^a   Peterson, T ^a  

^a Department of Computer Science   (United States)

Author keywords

Averaging; Gating; Neural networks; Partitioning; Reinforcement learning; Weighting

Indexed keywords

APPROXIMATION THEORY; ARTIFICIAL INTELLIGENCE; COMPUTATIONAL COMPLEXITY; FUNCTIONS; HEURISTIC METHODS; MATHEMATICAL MODELS; NEURAL NETWORKS; STATE SPACE METHODS;

MULTIPLE AGENTS; PARTITIONING; REINFORCEMENT LEARNING;

LEARNING SYSTEMS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; AVERAGING; DISCRIMINANT ANALYSIS; MATHEMATICAL MODEL; PRIORITY JOURNAL;

EID: 0032772352     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00024-6     Document Type: Article

References (70)

1. Albus J. A new approach to manipulator control: the cerebellar model articulation control. Journal of Dynamic Systems Measure and Control. 97:1975;270-277.
2. Atkeson, C., Moore, A., and Schaal, S. (1997). Locally weighted regression. Artificial Intelligence Review.
3. Bellman R. Dynamic programming. 1957;Princeton University Press, Princeton, NJ.
4. Bertsekas D., Tsitsiklis J. Neuro-dynamic programming. 1996;Athena Scientific, Belmont, MA.
5. Blanzieri E., Katenkamp P. Learning radial basis function networks on-line. Proceedings of International Conference on machine Learning. 1996;Morgan Kaufmann, San Francisco, CA. pp. 37-45.
6. Boyan J., Moore A. Generalization in reinforcement learning: safely approximating the value function. Tesauro J., Touretzky D., Leen T. Neural Information Processing Systems. 7:1995;369 MIT Press, Cambridge, MA.
7. Breiman L. Bagging predictors. Machine Learning. 24:1996;123-140.
8. Breiman L. Stacked regressions. Machine Learning. 24:1996;49-64.
9. Breiman, L. (1996c). Bias, variance and arcing classifiers. Technical Report 460. Berkeley: University of California.
10. Breiman L., Friedman L., Stone P. Classification and regression. 1984;Wadsworth, Belmont, CA.
11. Chrisman L. Reinforcement learning with perceptual aliasing: the perceptual distinction approach. Proceedings of AAAI. 1993;Morgan Kaufmann, San Francisco, CA. pp. 183-188.
12. Dayan P., Hinton G. Feudal reinforcement learning. Neural Information Processing Systems. 1993;MIT Press, Cambridge, MA.
13. Dietterich, T. (1997). Hierarchical reinforcement learning with MAXQ value function decomposition. Technical report. ftp://www.cs.orst.edu/.
14. Dorigo, M., and Gambardella, L. (1995). Ant-Q: a reinforcement learning approach to combinatorial optimization. Technical Report 95-01. Belgium: Universite Libre de Bruxelles.
15. Drucker H. Improving regressors using boosting techniques. Proceedings of ICML'97. 1997;Morgan Kaufmann, San Francicso, CA. pp. 107-115.
16. Erickson, M., and Kruschke, J. (1996). Rules and examplars in category learning (Manuscript).
17. Freund Y., Schapire R. Experiments with a new boosting algorithm. Proceedings of ICML'97. 1996;Morgan Kaufmann, San Francisco, CA. pp. 148-156.
18. Hashem, S. (1993). Optimal linear combinations of neural networks. PhD Thesis, Purdue, Indiana: Purdue University.
19. Hertz J., Krogh A., Palmer R. Introduction to the theory of neural computation. 1991;Addison-Wesley, Reading, MA.
20. Humphrys, M. (1996). W-learning: a simple RL-based society of mind. Technical report 362, Cambridge, UK: University of Cambridge, Computer Laboratory.
21. Jacobs R. Bias/variance analysis of mixtures-of-experts architectures. Neural Computation. 9:1997;369-383.
22. Jacobs R., Jordan M., Nowlan S., Hinton G. Adaptive mixtures of local experts. Neural Computation. 3:1991;79-87.
23. Jordan M., Jacobs R. Hierarchical mixtures of experts and the EM algorithm. Neural Computation. 6:1994;181-214.
24. Kaelbling L., Littman M., Moore A. Reinforcement learning: A survey. Journal of Artificial Intelligence Research. 4:1996;237-285.
25. Krogh A., Vedelsby J. Neural network ensembles, cross validation, and active learning. Neural Information Processing Systems. 1995;MIT Press, Cambridge, MA. pp. 231-238.
26. Kubat, M. (1997). Decision trees can initialize radial-basis-function networks (Manuscript).
27. Lane, S., Handelman, D., & Gelfand, J. (1992). Theory and development of higher-order CMAC neural networks. IEEE Control Systems, pp. 23-31.
28. Lin L. Self-improving reactive agents based on reinforcement learning, planning, and teaching. Machine Learning. 8:1992;293-321.
29. Margineantu D., Dietterich T. Pruning adaptive boosting. Proceedings of ICML. 1997;Morgan Kaufmann, San Francisco, CA. pp. 211-218.
30. Mataric M. Reward functions for accelerated learning. Proceedings Conference on Simulation of Adaptive Behaviour. 1995;MIT Press, Cambridge, MA.
31. McCallum A. Learning to use selective attention and short-term memory in sequential tasks. Proceedings of the conference on Simulation of Adaptive Behavior. 1996;MIT Press, Cambridge, MA. pp. 315-324.
32. Meir R. Bias, variance and the combination of least squares estimators. Neural Information Processing Systems. 1995;MIT Press, Cambridge, MA. pp. 295-302.
33. Parmanto B., Munro P., Doyle H. Reducing variance of committee prediction with resampling techniques. Connection Science. 8:(3/4):1996;405-426.
34. Perrone, M. (1993). Improving regression estimation: averaging methods for variance reduction with extensions to general convex measure optimization. PhD Thesis, Brown University. Providence, RI.
35. Peterson T., Sun R. An RBF network alternative to a hybrid architecture. Anchorage, Alaska. Proceedings of IEEE International Conference on Neural Networks. 1998;IEEE Press, Piscataway, NJ.
36. Poggio T., Girosi F. Networks for approximation and learning. Proceedings of IEEE. 78:(9):1990;1481-1497.
37. Quinlan R. Inductive learning of decision trees. Machine Learning. 1:1986;81-106.
38. Quinlan R. Bagging, Boosting and C4.5. Proceedings of AAAI'96. 1996;Morgan Kaufmann, San Francisco, CA. pp. 725-730.
39. Raviv Y., Intrator N. Bootstrapping with noise: an effective regularization technique. Connection Science. 8:(3/4):1996;355-372.
40. Reddy C., Tadepalli P. Learning goal-decomposition rules using exercises. Proceedings of ICML'97. 1997;Morgan Kaufmann, San Francisco, CA. pp. 278-286.
41. Rosca, J. (1997). Hierarchical learning with procedural abstraction mechanisms. PhD Thesis, Rochester, NY: Department of Computer Science, University of Rochester.
42. Rosen B. Ensemble learning using decorrelated neural networks. Connection Science. 8:(3/4):1996;373-384.
43. Sanger T. Tree-structured adaptive networks for function approximation in high-dimensional spaces. IEEE Transaction on Neural Networks. 2:(2):1991;285-293.
44. Schaal S., Atkeson C. From isolation to cooperation: an alternative view of a system of experts. Advances in Neural Information Processing Systems. 1996;MIT Press, Cambridge, MA. pp. 605-611.
45. Shcapire R., Freund Y., Bartlett P., Lee W. Boosting the margin: a new explanation for the effectiveness of voting methods. Proceedings of International Conference on Machine Learning. 1997;Morgan Kaufmann, San Francisco. pp. 322-330.
46. Singh, S. (1994). Learning to solve Markovian decision processes. PhD Thesis, Amherst, MA: University of Massachusetts.
47. Singh S., Jaakkola T., Jordan M. Reinforcement learning with soft state aggregation. Hanson S.L., Cowan J.C., Giles L. Advances in Neural Information Processing Systems. 1994;Morgan Kaufmann, San Mateo, CA.
48. Sun, R. (1997). Planning from reinforcement learning. Technical report TR-CS-97-0027, Tuscaloosa, AL: University of Alabama.
49. Sun R., Bookman L. Computational architectures integrating neural and symbolic procedures. 1994;Kluwer Academic Publishers, Norwell, MA.
50. Sun R., Peterson T. A hybrid agent architecture for reactive sequential decision making. Sun R., Alexandre F. Connectionist-symbolic integration. 1997;Lawrence Erlbaum Associates, Hillsdale, NJ.
51. Sun R., Peterson T. A hybrid model for learning sequential navigation. Monterey, CA Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA'97). 1997;IEEE Press, Piscateway, NJ. pp. 234-239.
52. Sun R., Peterson T. Some experiments with a hybrid model for learning sequential decision making. Information Sciences. 111:1998;83-107.
53. Sun R., Peterson T., Merrill E. Bottom-up skill learning in reactive sequential decision tasks. Proceedings of 18th Cognitive Science Society Conference. 1996;Lawrence Erlbaum Associates, Hillsdale, NJ. pp. 684-690.
54. Sutton R. Integrated architectures for learning, planning. Proceedings of Seventh International Conference on Machine Learning and reacting based on approximating dynamic programming. 1990;Morgan Kaufmann, San Meteo, CA.
55. Sutton R. Generalization in reinforcement learning: successful examples using sparse coarse coding. Neural Information Processing Systems. 8:1996;MIT Press, Cambridge, MA.
56. Tadepalli P., Dietterich T. Hierarchical explanation-based reinforcement learning. Proceedings International Conference on machine Learning. 1997;Morgan Kaufmann, San Francisco. pp. 358-386.
57. Takagi T., Sugeno M. Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems Man and Cybernetics. 15:(1):1985;116-132.
58. Taniguchi M., Tresp V. Averaging regularized estimators. Neural Computation. 9:1997;1163-1178.
59. Tham C. Reinforcement learning of multiple tasks using a hierarchical CMAC architecture. Robotics and Autonomous Systems. 15:1995;247-274.
60. Thrun S., Schwartz A. Finding structure in reinforcement learning. Neural Information Processing Systems. 7:1995;MIT Press, Cambridge, MA.
61. Ting W.K., Witten I. Stacking bagged and dagged models. Proceedings of ICML'97. 1997;Morgan Kaufmann, San Francisco, CA. pp. 367-375.
62. Tresp V., Taniguchi M. Combining estimators using non-constant weighting functions. Neural Information Processing Systems. 7:1995;MIT Press, Cambridge, MA. pp. 419-426.
63. Tumer K., Ghosh J. Error correlation and error reduction in ensemble classifiers. Connection Science. 8:(3/4):1996;385-404.
64. Ueda N., Nakano R. Generalization error of ensemble estimators. IEEE International Conference on Neural Networks. 1996;IEEE Press, Piscateway, NJ. pp. 90-95.
65. van der Smagt P., Groen F. Approximation with neural networks. Proceedings of 1995 International Conference on Neural Networks. 1995;IEEE Press, Piscateway, NJ.
66. Watkins, C. (1989). Learning with delayed rewards. PhD Thesis, Cambridge, UK: Cambridge University.
67. Wiering, M., and Schmidhuber, J. (1996). HQ-learning. TR IDSIA-95-96.
68. Whitehead A. A complexity analysis of cooperative mechanisms in reinforcement learning. Proceedings of the AAAI'93. 1993;Morgan Kaufmann, San Francisco, CA. pp. 607-613.
69. Wolpert D. Stacked generalization. Neural Networks. 5:1992;241-259.
70. Xu L., Jordan M., Hinton G. An alternative model for mixtures of experts. Neural Information Processing Systems. 7:1995;MIT Press, Cambridge, MA. pp. 633-640.