Reinforcement Learning

Policy gradients, value-based methods, control, game playing.

A topic in the Science corpus, drawn from 2,212 papers.

Trusted voices in Reinforcement Learning

Ordered by the trust Reinforcement Learning's own network concentrates on each researcher, most first.

  1. Richard S. Sutton — trusted by 4,431 researchers here
  2. Andrew Barto — trusted by 3,390 researchers here
  3. Ronald J. Williams — trusted by 2,872 researchers here
  4. Sergey Levine — trusted by 2,478 researchers here
  5. Pieter Abbeel — trusted by 2,595 researchers here
  6. David Silver — trusted by 2,168 researchers here
  7. Satinder Singh — trusted by 1,925 researchers here
  8. Martin A. Riedmiller — trusted by 1,400 researchers here
  9. John Schulman — trusted by 1,573 researchers here
  10. Jan Peters — trusted by 1,354 researchers here
  11. R´emi Munos — trusted by 1,215 researchers here
  12. Stefan Schaal — trusted by 1,270 researchers here

Most-cited papers in Reinforcement Learning

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Human-level control through deep reinforcement learning (2015) — 32,431 citations
  2. Proximal Policy Optimization Algorithms (2017, arXiv.org) — 29,461 citations
  3. Mastering the game of Go with deep neural networks and tree search (2016) — 19,057 citations
  4. Continuous control with deep reinforcement learning (2015, International Conference on Learning Representations) — 15,687 citations
  5. Playing Atari with Deep Reinforcement Learning (2013, arXiv.org) — 13,852 citations
  6. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor (2018, International Conference on Machine Learning) — 11,773 citations
  7. Mastering the game of Go without human knowledge (2017) — 10,580 citations
  8. Asynchronous Methods for Deep Reinforcement Learning (2016) — 10,169 citations
  9. Deep Reinforcement Learning with Double Q-Learning (2015) — 9,251 citations
  10. Trust Region Policy Optimization (2015, International Conference on Machine Learning) — 8,139 citations
  11. Probabilistic robotics (2002) — 7,585 citations
  12. Finite-time Analysis of the Multiarmed Bandit Problem (2002) — 7,574 citations
  13. Addressing Function Approximation Error in Actor-Critic Methods (2018) — 7,119 citations
  14. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017) — 6,086 citations
  15. Deep Reinforcement Learning from Human Preferences (2017, Neural Information Processing Systems) — 5,646 citations
  16. OpenAI Gym (2016) — 5,596 citations
  17. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (2025, Nature) — 5,477 citations
  18. High-Dimensional Continuous Control Using Generalized Advantage Estimation (2015) — 4,662 citations
  19. End to End Learning for Self-Driving Cars (2016) — 4,658 citations
  20. Deterministic Policy Gradient Algorithms (2014) — 4,557 citations
  21. Prioritized Experience Replay (2015) — 4,495 citations
  22. Dueling Network Architectures for Deep Reinforcement Learning (2015) — 4,476 citations
  23. Grandmaster level in StarCraft II using multi-agent reinforcement learning (2019) — 4,437 citations
  24. Reflexion: language agents with verbal reinforcement learning (2023) — 4,400 citations
  25. A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning (2010) — 4,272 citations
  26. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022, arXiv.org) — 4,254 citations
  27. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play (2018) — 4,131 citations
  28. A survey of robot learning from demonstration (2009) — 4,034 citations
  29. Neuro-Dynamic Programming (2009) — 4,030 citations
  30. Bandit Based Monte-Carlo Planning (2006) — 3,947 citations
  31. Domain randomization for transferring deep neural networks from simulation to the real world (2017) — 3,883 citations
  32. End-to-End Training of Deep Visuomotor Policies (2015) — 3,853 citations
  33. Reinforcement learning in robotics: A survey (2013) — 3,794 citations
  34. Generative Adversarial Imitation Learning (2016) — 3,722 citations
  35. Apprenticeship learning via inverse reinforcement learning (2004) — 3,716 citations
  36. Optimization as a Model for Few-Shot Learning (2016) — 3,710 citations
  37. Gradient Episodic Memory for Continual Learning (2017) — 3,589 citations
  38. A Brief Survey of Deep Reinforcement Learning (2017) — 3,581 citations
  39. Maximum Entropy Inverse Reinforcement Learning (2008) — 3,476 citations
  40. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022) — 3,376 citations
  41. Reinforcement learning (2019) — 3,375 citations
  42. The Arcade Learning Environment: An Evaluation Platform for General Agents (2012) — 3,357 citations
  43. Soft Actor-Critic Algorithms and Applications (2018) — 3,200 citations
  44. Curiosity-Driven Exploration by Self-Supervised Prediction (2017) — 3,014 citations
  45. Stable-Baselines3: Reliable Reinforcement Learning Implementations (2021) — 2,998 citations
  46. Hindsight Experience Replay (2017) — 2,808 citations
  47. The Nonstochastic Multiarmed Bandit Problem (2002) — 2,743 citations
  48. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020, arXiv.org) — 2,718 citations
  49. A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010) — 2,681 citations
  50. Conservative Q-Learning for Offline Reinforcement Learning (2020, Neural Information Processing Systems) — 2,669 citations

Most active researchers

By papers in this topic: a volume measure, not trust.