Prehistory — From Neural Networks to the TransformerVolodymyr Mnih et al. (Google DeepMind)Google DeepMind
Human-level control through deep reinforcement learning
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Human-level control through deep reinforcement learning — published in Nature, 49 Atari games
Why it matters
The point at which deep reinforcement learning passed peer review and was recognized as an official achievement
Source — Primary sources first; secondary reports are labelled “Press”
Papernature.comhttps://www.nature.com/articles/nature14236Added in Week 35, 2026 · See that week
On the map — ⓪ Prehistory line
- Previous stopNeural Machine Translation by Jointly Learning to Align and Translate
- This recordHuman-level control through deep reinforcement learning
- Next stopGoogle publishes Distilling the Knowledge in a Neural Network on arXiv