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.
- Richard S. Sutton — trusted by 4,431 researchers here
- Andrew Barto — trusted by 3,390 researchers here
- Ronald J. Williams — trusted by 2,872 researchers here
- Sergey Levine — trusted by 2,478 researchers here
- Pieter Abbeel — trusted by 2,595 researchers here
- David Silver — trusted by 2,168 researchers here
- Satinder Singh — trusted by 1,925 researchers here
- Martin A. Riedmiller — trusted by 1,400 researchers here
- John Schulman — trusted by 1,573 researchers here
- Jan Peters — trusted by 1,354 researchers here
- R´emi Munos — trusted by 1,215 researchers here
- 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.
- Human-level control through deep reinforcement learning (2015) — 32,431 citations
- Proximal Policy Optimization Algorithms (2017, arXiv.org) — 29,461 citations
- Mastering the game of Go with deep neural networks and tree search (2016) — 19,057 citations
- Continuous control with deep reinforcement learning (2015, International Conference on Learning Representations) — 15,687 citations
- Playing Atari with Deep Reinforcement Learning (2013, arXiv.org) — 13,852 citations
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor (2018, International Conference on Machine Learning) — 11,773 citations
- Mastering the game of Go without human knowledge (2017) — 10,580 citations
- Asynchronous Methods for Deep Reinforcement Learning (2016) — 10,169 citations
- Deep Reinforcement Learning with Double Q-Learning (2015) — 9,251 citations
- Trust Region Policy Optimization (2015, International Conference on Machine Learning) — 8,139 citations
- Probabilistic robotics (2002) — 7,585 citations
- Finite-time Analysis of the Multiarmed Bandit Problem (2002) — 7,574 citations
- Addressing Function Approximation Error in Actor-Critic Methods (2018) — 7,119 citations
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017) — 6,086 citations
- Deep Reinforcement Learning from Human Preferences (2017, Neural Information Processing Systems) — 5,646 citations
- OpenAI Gym (2016) — 5,596 citations
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (2025, Nature) — 5,477 citations
- High-Dimensional Continuous Control Using Generalized Advantage Estimation (2015) — 4,662 citations
- End to End Learning for Self-Driving Cars (2016) — 4,658 citations
- Deterministic Policy Gradient Algorithms (2014) — 4,557 citations
- Prioritized Experience Replay (2015) — 4,495 citations
- Dueling Network Architectures for Deep Reinforcement Learning (2015) — 4,476 citations
- Grandmaster level in StarCraft II using multi-agent reinforcement learning (2019) — 4,437 citations
- Reflexion: language agents with verbal reinforcement learning (2023) — 4,400 citations
- A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning (2010) — 4,272 citations
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022, arXiv.org) — 4,254 citations
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play (2018) — 4,131 citations
- A survey of robot learning from demonstration (2009) — 4,034 citations
- Neuro-Dynamic Programming (2009) — 4,030 citations
- Bandit Based Monte-Carlo Planning (2006) — 3,947 citations
- Domain randomization for transferring deep neural networks from simulation to the real world (2017) — 3,883 citations
- End-to-End Training of Deep Visuomotor Policies (2015) — 3,853 citations
- Reinforcement learning in robotics: A survey (2013) — 3,794 citations
- Generative Adversarial Imitation Learning (2016) — 3,722 citations
- Apprenticeship learning via inverse reinforcement learning (2004) — 3,716 citations
- Optimization as a Model for Few-Shot Learning (2016) — 3,710 citations
- Gradient Episodic Memory for Continual Learning (2017) — 3,589 citations
- A Brief Survey of Deep Reinforcement Learning (2017) — 3,581 citations
- Maximum Entropy Inverse Reinforcement Learning (2008) — 3,476 citations
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022) — 3,376 citations
- Reinforcement learning (2019) — 3,375 citations
- The Arcade Learning Environment: An Evaluation Platform for General Agents (2012) — 3,357 citations
- Soft Actor-Critic Algorithms and Applications (2018) — 3,200 citations
- Curiosity-Driven Exploration by Self-Supervised Prediction (2017) — 3,014 citations
- Stable-Baselines3: Reliable Reinforcement Learning Implementations (2021) — 2,998 citations
- Hindsight Experience Replay (2017) — 2,808 citations
- The Nonstochastic Multiarmed Bandit Problem (2002) — 2,743 citations
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020, arXiv.org) — 2,718 citations
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010) — 2,681 citations
- 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.
- Sergey Levine — 136 papers
- Pieter Abbeel — 94 papers
- Richard S. Sutton — 55 papers
- David Silver — 53 papers
- R´emi Munos — 48 papers
- Chelsea Finn — 36 papers
- Jan Peters — 35 papers
- Satinder Singh — 35 papers
- Nicolas Manfred Otto Heess — 35 papers
- Lihong Li — 35 papers
- Peter Stone — 32 papers
- J. Urgen Schmidhuber — 32 papers