Atari games
Media
Classic video games like Space Invaders and Pong, used by DeepMind to train early AI systems that learned to play simply by observing pixels and rewards.
Mentioned in 4 videos
Videos Mentioning Atari games
Yann LeCun: Deep Learning, ConvNets, and Self-Supervised Learning | Lex Fridman Podcast #36
Lex Fridman
Mentioned as a benchmark for reinforcement learning, where systems require significant training time to reach human-level performance.
Ilya Sutskever: OpenAI Meta-Learning and Self-Play | MIT Artificial General Intelligence (AGI)
Lex Fridman
A collection of classic video games where reinforcement learning algorithms have been trained and evaluated.
CEO Of Microsoft AI: AI Is Becoming More Dangerous And Threatening! - Mustafa Suleyman
The Diary Of A CEO
Classic video games like Space Invaders and Pong, used by DeepMind to train early AI systems that learned to play simply by observing pixels and rewards.
François Chollet: ARC-AGI-3, Beyond Deep Learning & A New Approach To ML
Y Combinator
DeepMind's early work in 2013 on solving these games using deep reinforcement learning is cited as a pioneering effort in using AI for game-playing.