Why most decisions are easy in tetris - and perhaps in other sequential decision problems, as well (2016)
Authors
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 preva-lent in the game: simple dominance, cumulative dominance, and noncompensation. These condi-tions 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 en-counter, it is unlikely that Tetris is unique or rare in having these properties.
Bibliographic entry
Simsek, Ö., Algórta, S., & Kothiyal, A. (2016). Why most decisions are easy in tetris - and perhaps in other sequential decision problems, as well. In M. F. Balcan & K. Q. Weinberger (Eds.), Proceedings of the 33rd International Conference on Machine (JMLR Workshop and Conference Proceedings Vol. 48). Red Hook, NY: Curran. (Full text)
Miscellaneous
| Publication year | 2016 | |
|---|---|---|
| Document type: | In book | |
| Publication status: | Published | |
| External URL: | ||
| Categories: | ||
| Keywords: |