Why did TD-Gammon work?

Advances in Neural Information Processing Systems

Volumn , Issue , 1997, Pages 10-16

  Pollack, Jordan B ^a   Blair, Alan D ^a  

^a BRANDEIS UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CO-EVOLUTIONARY; EVALUATION FUNCTION; HILL CLIMBING; LEARNING TASKS; TEMPORAL DIFFERENCE LEARNING;

LEARNING SYSTEMS;

EID: 84899013439     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Angeline, P. J. (1994). An alternate interpretation of the iterated prisoners dilemma and the evolution of non-mutual cooperation. In Brooks, R. and Maes, P., editors, Proceedings 4th Artificial Life Conference, pages 353-358. MIT Press.
2. Angeline, P.J. and Pollack, J. B. (1994). Competitive environments evolve better solutions for complex tasks. In Forrest, S., editor, Genetic Algorithms: Proceedings of the Fifth Inter national Conference.
3. Boyan, J. A. (1992). Modular neural networks for learning context-dependent game strategies. Masters thesis, Computer Speech and Language Processing, Cambridge University.
4. Cliff, D. and Miller, G. (1995). Tracking the red queen: Measurements of adaptive progress in co-evolutionary simulations. In Third European Conference on Artificial Life, pages 200-218.
5. Hillis, D. (1992). Co-evolving parasites improves simulated evolution as an optimization procedure. In C. Langton, C. Taylor, J. F. and Rasmussen, S., editors, Artificial Life II. Addison-Wesley, Reading, MA.
6. International Business Machines (Sept. 12, 1995). IBMs family funpak for os/2 warp hits retail shelves.
7. Juille, H. and Pollack, J. (1995). Massively parallel genetic programming. In Angeline, P. and Kinnear, K., editors, Advances in Genetic Programming II. MIT Press, Cambridge.
8. Michie, D. (1961). Trial and error. In Science Survey, part 2, pages 129-145. Penguin.
9. Mitchell, M., Hraber, P. T., and Crutchfield, J. P. (1993). Revisiting the edge of chaos: Evolving cellular automata to perform computations. Complex Systems, 7.
10. Packard, N. (1988). Adaptation towards the edge of chaos. In Kelso, J. A. S., Mandell, A. J., and Shlesinger, M. F, editors, Dynamic patterns in complex systems, pages 293-301. World Scientific.
11. Reynolds, C. (1994). Competition, coevolution, and the game of tag. In Proceedings 4th Artificial Life Conference. MIT Press.
12. Rosin, C. D. and Belew, R. K. (1995). Methods for competitive co-evolution: finding opponents worth beating. In Proceedings of the 6th international conference on Genetic Algorithms, pages 373-380. Morgan Kaufman.
13. Samuel, A. L. (1959). some studies of machine learning using the game of checkers. IBM Joural of Research and Development.
14. Sims, K. (1994). Evolving 3d morphology and behavior by competition. In Brooks, R. and Maes, P., editors, Proceedings 4th Artificial Life Conference. MIT Press.
15. Tesauro, G. (1989). Connectionist learning of expert preferences by comparison training. In Touretzky, D., editor, Advances in Neural Information Processing Systems, volume 1, pages 99-106, Denver 1988. Morgan Kaufmann, San Mateo.
16. Tesauro, G. (1992). Practical issues in temporal difference learning. Machine Learning, 8:257-277.
17. Tesauro, G. (1995). Temporal difference learning and td-gammon. Communications of the ACM, 38(3):58-68.