Learning to Perform a Tetris with Deep Reinforcement Learning

Content Provider	Semantic Scholar
Author	Gordon, Daniel
Copyright Year	2018
Abstract	Video games and simulated environments have been a popular testing ground for many recent RL algorithms because of their speed, repeatability, and scalability. However many of the state-of-the-art algorithms still fail at games requiring longterm planning. In this work, I train an agent to consistently perform the eponymous Tetris (clearing 4 lines at once).
File Format	PDF HTM / HTML
Alternate Webpage(s)	https://homes.cs.washington.edu/~xkcd/papers/deep_rl_for_tetris.pdf
Language	English
Access Restriction	Open
Content Type	Text
Resource Type	Article