Abstract
In this paper we investigate reinforcement learning approaches for the popular computer game Tetris. User-defined reward functions have been applied to TD(0) learning based on ε-greedy strategies in the standard Tetris scenario. The numerical experiments show that reinforcement learning can significantly outperform agents utilizing fixed policies.
Chapter PDF
Similar content being viewed by others
References
Bellman, R.E.: Dynamic Programming. Dover Publications (2003)
Burgiel, H.: How to lose at Tetris. Mathematical Gazette 81, 194–200 (1997)
Demaine, E.D., Hohenberger, S., Liben-Nowell, D.: Tetris is hard, even to approximate. In: Warnow, T.J., Zhu, B. (eds.) COCOON 2003. LNCS, vol. 2697, Springer, Heidelberg (2003)
Faußer, S., Schwenker, F.: Neural approximation of Monte Carlo policy evaluation deployed in Connect Four. In: Prevost, L., Marinai, S., Schwenker, F. (eds.) ANNPR 2008. LNCS (LNAI), vol. 5064, pp. 90–100. Springer, Heidelberg (2008)
Faußer, S., Schwenker, F.: Learning a strategy with neural approximated temporal-difference methods in English Draughts. In: 2010 20th International Conference on Pattern Recognition (ICPR), pp. 2925–2928. IEEE (2010)
Faußer, S., Schwenker, F.: Ensemble methods for reinforcement learning with function approximation. In: Sansone, C., Kittler, J., Roli, F. (eds.) MCS 2011. LNCS, vol. 6713, pp. 56–65. Springer, Heidelberg (2011)
Faußer, S., Schwenker, F.: Neural network ensembles in reinforcement learning. Neural Processing Letters, 1–15 (2013)
Groß, A., Friedland, J., Schwenker, F.: Learning to play Tetris applying reinforcement learning methods. In: ESANN, pp. 131–136 (2008)
Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)
Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58–68 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Thiam, P., Kessler, V., Schwenker, F. (2014). A Reinforcement Learning Algorithm to Train a Tetris Playing Agent. In: El Gayar, N., Schwenker, F., Suen, C. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2014. Lecture Notes in Computer Science(), vol 8774. Springer, Cham. https://doi.org/10.1007/978-3-319-11656-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-11656-3_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11655-6
Online ISBN: 978-3-319-11656-3
eBook Packages: Computer ScienceComputer Science (R0)