A deep Q-network learns Atari control policies from raw pixels and beats prior algorithms on six games while surpassing humans on three.
An analysis of temporal-difference learning with function approximation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2013 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Playing Atari with Deep Reinforcement Learning
A deep Q-network learns Atari control policies from raw pixels and beats prior algorithms on six games while surpassing humans on three.