Atari, every mention
6 scenes, the whole family · ← back to Atari
tap a year for its mentions
every year anyone Murray Shanahan 3Demis Hassabis 3François Chollet 2Wojciech Zaremba 1
Verbatim, from the transcripts: the passages where Atari comes up
Demis Hassabis: Agents, AGI & The Next Big Scientific Breakthrough · Y Combinator
- ▶ 4:14 Demis Hassabis Atari program, DQN, one of the ways it was able to master Atari games was by doing experience replay. 2 times in the scene
- ▶ 6:34 Demis Hassabis So all of the Atari work and AlphaGo, most specifically, they're agent systems.
François Chollet: Why Scaling Alone Isn’t Enough for AGI · Y Combinator
- ▶ 32:57 François Chollet Uh, Atari games, right back in, you know, they were very, very early, very visionary in that sense to work on, on this problem so early with these methods, which are still very modern methods. 2 times in the scene
Ex Machina's Scientific Advisor - Murray Shanahan · Y Combinator
- ▶ 6:13 Murray Shanahan For example, if you, if, if a lot of this, a lot of work here at DeepMind has been done with these Atari retro, uh, computer games.
- ▶ 44:21 Murray Shanahan About, so they published this paper about, um, a system that could learn to play these retro Atari games completely from scratch. 2 times in the scene
An AI Primer with Wojciech Zaremba · Y Combinator
- ▶ 5:59 Wojciech Zaremba These are, uh, these are, like, the initial results are coming from DeepMind, uh, and, um, but, but simultaneously, um, simultaneously, it takes extremely long time, like, in terms of real-time execution, to learn to play computer games,…