Abstract

An artificial agent is developed that learns to play a diverse range of classic Atari 2600 computer games directly from sensory experience, achieving a performance comparable to that of an expert human player; this work paves the way to building general-purpose learning algorithms that bridge the divide between perception and action.

Description

Human-level control through deep reinforcement learning | Nature

Links and resources

DOI:
10.1038/nature14236
URL:
additional links:
BibTeX key:
mnih2015humanlevel
search on:

Comments and Reviews  
(0)

There is no review or comment yet. You can write one!

Tags


Cite this publication