Approximate dynamic programming finally performswell in the game of Tetris

Advances in Neural Information Processing Systems

Volumn , Issue , 2013, Pages

  Gabillon, Victor ^a   Ghavamzadeh, Mohammad ^a   Scherrer, Bruno ^b  

^a INRIA   (France)

^b INRIA   (France)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; HUMAN COMPUTER INTERACTION; OPTIMIZATION;

APPROXIMATE DYNAMIC PROGRAMMING; BLACK BOXES; CROSS-ENTROPY METHOD; GENERATIVE MODEL; MODIFIED POLICY ITERATIONS; OPTIMIZATION TECHNIQUES; VALUE FUNCTIONS; VIDEO GAME;

ITERATIVE METHODS;

EID: 84898951107     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. D. Bertsekas and S. Ioffe. Temporal differences-based policy iteration and applications in neuro-dynamic programming. Technical report, MIT, 1996.
2. D. Bertsekas and J. Tsitsiklis. Neuro-Dynamic Programming. Athena Scientific, 1996.
3. H. Burgiel. How to Lose at Tetris. Mathematical Gazette, 81:194-200, 1997.
4. E. Demaine, S. Hohenberger, and D. Liben-Nowell. Tetris is hard, even to approximate. In Proceedings of the Ninth International Computing and Combinatorics Conference, pages 351-363, 2003.
5. C. Fahey. Tetris AI, Computer plays Tetris, 2003. http://colinfahey.com/ tetris/tetris.html.
6. V. Farias and B. van Roy. Tetris: A study of randomized constraint sampling. Springer-Verlag, 2006.
7. A. Fern, S. Yoon, and R. Givan. Approximate Policy Iteration with a Policy Language Bias: Solving Relational Markov Decision Processes. Journal of Artificial Intelligence Research, 25:75-118, 2006.
8. T. Furmston and D. Barber. A unifying perspective of parametric policy search methods for Markov decision processes. In Proceedings of the Advances in Neural Information Processing Systems, pages 2726-2734, 2012.
9. V. Gabillon, A. Lazaric, M. Ghavamzadeh, and B. Scherrer. Classification-based policy iteration with a critic. In Proceedings of ICML, pages 1049-1056, 2011.
10. N. Hansen and A. Ostermeier. Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation, 9:159-195, 2001.
11. S. Kakade. A natural policy gradient. In Proceedings of the Advances in Neural Information Processing Systems, pages 1531-1538, 2001.
12. M. Lagoudakis and R. Parr. Reinforcement Learning as Classification: Leveraging Modern Classifiers. In Proceedings of ICML, pages 424-431, 2003.
13. A. Lazaric, M. Ghavamzadeh, and R. Munos. Analysis of a Classification-based Policy Iteration Algorithm. In Proceedings of ICML, pages 607-614, 2010.
14. M. Puterman and M. Shin. Modified policy iteration algorithms for discounted Markov decision problems. Management Science, 24(11), 1978.
15. R. Rubinstein and D. Kroese. The cross-entropy method: A unified approach to combinatorial optimization, Monte-Carlo simulation, and machine learning. Springer-Verlag, 2004.
16. B. Scherrer. Performance Bounds for λ-Policy Iteration and Application to the Game of Tetris. Journal of Machine Learning Research, 14:1175-1221, 2013.
17. B. Scherrer, M. Ghavamzadeh, V. Gabillon, and M. Geist. Approximate modified policy iteration. In Proceedings of ICML, pages 1207-1214, 2012.
18. I. Szita and A. Lorincz. Learning Tetris Using the Noisy Cross-Entropy Method. Neural Computation, 18(12):2936-2941, 2006.
19. C. Thiery and B. Scherrer. Building Controllers for Tetris. International Computer Games Association Journal, 32:3-11, 2009.
20. C. Thiery and B. Scherrer. Improvements on Learning Tetris with Cross Entropy. International Computer Games Association Journal, 32, 2009.
21. C. Thiery and B. Scherrer. MDPTetris features documentation, 2010. http://mdptetris.gforge.inria.fr/doc/feature-functions-8h.html.
22. J. Tsitsiklis and B Van Roy. Feature-based methods for large scale dynamic programming. Machine Learning, 22:59-94, 1996.