Peter Sunehag

Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward

Peter Sunehag, Guy Lever, Audrūnas Gruslys et al. · 2018 · 474 citations

Reinforcement Learning in Large Discrete Action Spaces.

Gabriel Dulac-Arnold, Peter Sunehag, Ben Coppin · arXiv (Cornell University) · 2015 · 287 citations · Full text

Natural Language Processing, Artificial Intelligence, Large Ai Model +15

Deep Reinforcement Learning in Large Discrete Action Spaces

Gabriel Dulac-Arnold, Hado van Hasselt, Peter Sunehag et al. · arXiv (Cornell University) · 2015 · 265 citations · Full text

Artificial Intelligence, Natural Language Processing, Large Ai Model +15

Wearable sensor activity analysis using semi-Markov models with a grammar

Owen Thomas, Peter Sunehag, Gideon Dror et al. · Pervasive and Mobile Computing · 2010 · 34 citations

Wearable System, Mobile Sensing, Engineering +11

The Sample-Complexity of General Reinforcement Learning

Tor Lattimore, Marcus Hütter, Peter Sunehag · arXiv (Cornell University) · 2013 · 33 citations · Full text

Mathematical Programming, Engineering, Machine Learning +14