Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well

Özgür Şimşek, Simón Algorta, Amit Kothiyal
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:1757-1765, 2016.

Abstract

We examined the sequence of decision problems that are encountered in the game of Tetris and found that most of the problems are easy in the following sense: One can choose well among the available actions without knowing an evaluation function that scores well in the game. This is a consequence of three conditions that are prevalent in the game: simple dominance, cumulative dominance, and noncompensation. These conditions can be exploited to develop faster and more effective learning algorithms. In addition, they allow certain types of domain knowledge to be incorporated with ease into a learning algorithm. Among the sequential decision problems we encounter, it is unlikely that Tetris is unique or rare in having these properties.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-simsek16, title = {Why Most Decisions Are Easy in Tetris---And Perhaps in Other Sequential Decision Problems, As Well}, author = {Şimşek, Özgür and Algorta, Simón and Kothiyal, Amit}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {1757--1765}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/simsek16.pdf}, url = {https://proceedings.mlr.press/v48/simsek16.html}, abstract = {We examined the sequence of decision problems that are encountered in the game of Tetris and found that most of the problems are easy in the following sense: One can choose well among the available actions without knowing an evaluation function that scores well in the game. This is a consequence of three conditions that are prevalent in the game: simple dominance, cumulative dominance, and noncompensation. These conditions can be exploited to develop faster and more effective learning algorithms. In addition, they allow certain types of domain knowledge to be incorporated with ease into a learning algorithm. Among the sequential decision problems we encounter, it is unlikely that Tetris is unique or rare in having these properties.} }
Endnote
%0 Conference Paper %T Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well %A Özgür Şimşek %A Simón Algorta %A Amit Kothiyal %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-simsek16 %I PMLR %P 1757--1765 %U https://proceedings.mlr.press/v48/simsek16.html %V 48 %X We examined the sequence of decision problems that are encountered in the game of Tetris and found that most of the problems are easy in the following sense: One can choose well among the available actions without knowing an evaluation function that scores well in the game. This is a consequence of three conditions that are prevalent in the game: simple dominance, cumulative dominance, and noncompensation. These conditions can be exploited to develop faster and more effective learning algorithms. In addition, they allow certain types of domain knowledge to be incorporated with ease into a learning algorithm. Among the sequential decision problems we encounter, it is unlikely that Tetris is unique or rare in having these properties.
RIS
TY - CPAPER TI - Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well AU - Özgür Şimşek AU - Simón Algorta AU - Amit Kothiyal BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-simsek16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 1757 EP - 1765 L1 - http://proceedings.mlr.press/v48/simsek16.pdf UR - https://proceedings.mlr.press/v48/simsek16.html AB - We examined the sequence of decision problems that are encountered in the game of Tetris and found that most of the problems are easy in the following sense: One can choose well among the available actions without knowing an evaluation function that scores well in the game. This is a consequence of three conditions that are prevalent in the game: simple dominance, cumulative dominance, and noncompensation. These conditions can be exploited to develop faster and more effective learning algorithms. In addition, they allow certain types of domain knowledge to be incorporated with ease into a learning algorithm. Among the sequential decision problems we encounter, it is unlikely that Tetris is unique or rare in having these properties. ER -
APA
Şimşek, Ö., Algorta, S. & Kothiyal, A.. (2016). Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:1757-1765 Available from https://proceedings.mlr.press/v48/simsek16.html.

Related Material