mlsanityData to 7 Oct 2026

Playing Atari with Deep Reinforcement Learning

arXiv 1312.5602 ↗First posted 19 Dec 2013cs.LGcited by 3,211

Not on the map. Why?

Cited by 252 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

Key facts. Cited by 3,211 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2016: 1; 2017: 2; 2018: 7; 2019: 8; 2020: 15; 2021: 592; 2022: 626; 2023: 602; 2024: 595; 2025: 504; 2026: 259.

3,211 papers.

Sort:

By area:

  1. 2017Deep reinforcement learning from human preferencescited by 3,846
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  5. 2023Consistency Modelscited by 1,778
  6. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  7. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  9. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  10. 2019Behavior Regularized Offline Reinforcement Learningcited by 654
  11. 2021Domain Generalization with MixStylecited by 563
  12. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
38 more
  1. 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 450
  2. 2023Learning Interactive Real-World Simulatorscited by 440
  3. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  4. 2022Temporal Difference Learning for Model Predictive Controlcited by 375
  5. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  6. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  7. 2018Reward learning from human preferences and demonstrations in Ataricited by 314
  8. 2023Tool Learning with Foundation Modelscited by 302
  9. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 292
  10. 2019Causal Confusion in Imitation Learningcited by 286
  11. 2019Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialogcited by 283
  12. 2021Ensemble deep learning: A reviewcited by 283
  13. 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 278
  14. 2021Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimismcited by 275
  15. 2025Learning to Reason under Off-Policy Guidancecited by 266
  16. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  17. 2023A Cookbook of Self-Supervised Learningcited by 248
  18. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  19. 2021Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithmscited by 222
  20. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 220
  21. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  22. 2022Multi-Game Decision Transformerscited by 212
  23. 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RLcited by 212
  24. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  25. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  26. 2022Active Example Selection for In-Context Learningcited by 195
  27. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  28. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  29. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 188
  30. 2025ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Modelscited by 187
  31. 2022In-context Reinforcement Learning with Algorithm Distillationcited by 186
  32. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  33. 2021Reinforcement Learning with Prototypical Representationscited by 179
  34. 2021Bilinear Classes: A Structural Framework for Provable Generalization in RLcited by 176
  35. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
  36. 2025Hierarchical Reasoning Modelcited by 167
  37. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  38. 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Designcited by 163

50 most cited of 3,211 All 3,211 (JSON)