Why most decisions are easy in Tetris—And perhaps in other sequential decision problems, as well

Özgür Şimşek; Simón Algorta; Amit Kothiyal

Why most decisions are easy in Tetris—And perhaps in other sequential decision problems, as well

Özgür Şimşek, Simón Algorta, Amit Kothiyal

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

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.

Original language	English
Title of host publication	Proceedings of The 33rd International Conference on Machine Learning
Publisher	PMLR
Pages	1757-1765
Number of pages	9
Volume	48
Publication status	Published - 30 Jun 2016

Publication series

Name	Proceedings of Machine Learning Research
ISSN (Print)	2640-3498

Keywords

sequential decision making; reinforcement learning; statistical structure of decision environments

Cite this

Şimşek, Ö., Algorta, S., & Kothiyal, A. (2016). Why most decisions are easy in Tetris—And perhaps in other sequential decision problems, as well. In Proceedings of The 33rd International Conference on Machine Learning (Vol. 48, pp. 1757-1765). (Proceedings of Machine Learning Research). PMLR.

Why most decisions are easy in Tetris—And perhaps in other sequential decision problems, as well. / Şimşek, Özgür; Algorta, Simón; Kothiyal, Amit.

Proceedings of The 33rd International Conference on Machine Learning. Vol. 48 PMLR, 2016. p. 1757-1765 (Proceedings of Machine Learning Research).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{162790aaba984ff7b8469cb232785175,

title = "Why most decisions are easy in Tetris—And perhaps in other sequential decision problems, as well",

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.",

keywords = "sequential decision making; reinforcement learning; statistical structure of decision environments",

author = "{\"O}zg{\"u}r Şimşek and Sim{\'o}n Algorta and Amit Kothiyal",

year = "2016",

month = "6",

day = "30",

language = "English",

volume = "48",

series = "Proceedings of Machine Learning Research",

publisher = "PMLR",

pages = "1757--1765",

booktitle = "Proceedings of The 33rd International Conference on Machine Learning",

}

TY - GEN

T1 - Why most decisions are easy in Tetris—And perhaps in other sequential decision problems, as well

AU - Şimşek, Özgür

AU - Algorta, Simón

AU - Kothiyal, Amit

PY - 2016/6/30

Y1 - 2016/6/30

N2 - 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.

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.

KW - sequential decision making; reinforcement learning; statistical structure of decision environments

M3 - Conference contribution

VL - 48

T3 - Proceedings of Machine Learning Research

SP - 1757

EP - 1765

BT - Proceedings of The 33rd International Conference on Machine Learning

PB - PMLR

ER -

Access to Document

http://proceedings.mlr.press/v48/simsek16.html