Re:Human-level control through deep reinforcement learning
by nl on Wednesday February 25, 2015 @04:03PM
(#9109574)
Is this a different paper to the original DeepMind video game paper? http://arxiv.org/abs/1312.5602
[ Parent
| on HN ]
Re:Human-level control through deep reinforcement learning
by sp332 on Wednesday February 25, 2015 @04:15PM
(#9109665)
Yes, I can't access the full paper but at least the figures are different :)
Edit: Ars Technica has a summary of this new paper. https://arstechnica.com/science/2015/02/ai-masters-49-atari-...
Re:Human-level control through deep reinforcement learning
by devindotcom on Wednesday February 25, 2015 @08:23PM
(#9110836)
Yes, they addressed this on the conference call I was on. That was a sort of 'initial results' they wanted to get out there, this is the full research. Same concept, explored more deeply.
Re:Human-level control through deep reinforcement learning
by Houshalter on Wednesday February 25, 2015 @04:32PM
(#9109770)
They claim good results on 49 games while the original paper only worked on a few IIRC.