Human learning in Atari
Name
Tsividis17.pdf
Size
1.12 MB
Format
Adobe PDF
Checksum (MD5)
03ac29c9a17fd18e1e471cb4e81a7f13
Author(s)
Pouncy, Thomas
Gershman, Samuel J.
Tsividis, Pedro
Xu, Jacqueline L.
Tenenbaum, Joshua B
Date Issued
2017
Journal
2017 AAAI Spring Symposium Series, Science of Intelligence: Computational Principles of Natural and Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence
Citation
Tsividis, Pedro A. et al. "Human learning in Atari." 2017 AAAI Spring Symposium Series, Science of Intelligence: Computational Principles of Natural and Artificial Intelligence, Technical Report SS-17-07 (2017) © 2017 Association for the Advancement of Artificial Intelligence
Version
Author's final manuscript
Abstract
Atari games are an excellent testbed for studying intelligent behavior, as they offer a range of tasks that differ widely in their visual representation, game dynamics, and goals presented to an agent. The last two years have seen a spate of research into artificial agents that use a single algorithm to learn to play these games. The best of these artificial agents perform at better-than-human levels on most games, but require hundreds of hours of game-play experience to produce such behavior. Humans, on the other hand, can learn to perform well on these tasks in a matter of minutes. In this paper we present data on human learning trajectories for several Atari games, and test several hypotheses about the mechanisms that lead to such rapid learning.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://aaai.org/ocs/index.php/SSS/SSS17/paper/viewFile/15280/14616
