{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2013-12-19-dqn-atari/","md":"https://postcutoff.com/e/2013-12-19-dqn-atari/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2013-12-19-dqn-atari","date":"2013-12-19","date_precision":"day","short_title":"DeepMind's DQN learns to play Atari games from pixels","deck":null,"takeaway":"DeepMind combined deep convolutional networks with Q-learning (DQN) to learn Atari 2600 games directly from screen pixels; the 2015 Nature version reached human-level performance on many of 49 games.","category":"research","category_label":"Research","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Playing Atari with Deep Reinforcement Learning (arXiv)","url":"https://arxiv.org/abs/1312.5602","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Human-level control through deep reinforcement learning (Nature, DOI)","url":"https://doi.org/10.1038/nature14236","type":"paper","group":"primary","domain":"doi.org"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["DeepMind"],"title":"DeepMind's DQN learns to play Atari games from pixels","summary":"DeepMind combined deep convolutional networks with Q-learning (DQN) to learn Atari 2600 games directly from screen pixels; the 2015 Nature version reached human-level performance on many of 49 games.","key_facts":["arXiv 1312.5602 'Playing Atari with Deep Reinforcement Learning' (December 2013)","Nature paper 'Human-level control through deep reinforcement learning' (February 2015)","Same architecture and hyperparameters across all games","Google acquired DeepMind in early 2014"],"key_numbers":[],"tags":["reinforcement-learning","games","deep-learning"],"science":null,"body_md":"## What happened\n\nDQN used experience replay and a target network to stabilize training of a deep Q-network on raw pixels and game score.\n\n## Why it matters\n\nLaunched deep reinforcement learning as a field and put DeepMind on the path to AlphaGo.","disputed":[],"related":[{"id":"2016-03-15-alphago-lee-sedol","url":"https://postcutoff.com/e/2016-03-15-alphago-lee-sedol/","date":"2016-03-15","date_precision":"day","short_title":"AlphaGo defeats Lee Sedol 4–1 at Go","deck":null,"takeaway":"A watershed for deep reinforcement learning and a 'Sputnik moment' that spurred massive AI investment, particularly in China.","category":"milestone","category_label":"Milestones","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google DeepMind"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/deepmind-dqn-learns-play"}