mlsanityData to 13 Oct 2026

A Brief Survey of Deep Reinforcement Learning

arXiv 1708.05866 ↗First posted 19 Aug 2017cs.LG cs.AI cs.CVcited by 466

Not on the map. Why?

Cited by 101 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep Q-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.

Key facts. Cited by 466 papers in the map (data through 13 Oct 2026). First posted on arXiv 19 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 1; 2021: 82; 2022: 89; 2023: 95; 2024: 110; 2025: 76; 2026: 12.

466 papers.

Sort:

By area:

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,135
  2. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 604
  3. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Promptscited by 394
  4. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 338
  5. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 277
  6. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 228
  7. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  8. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activitiescited by 154
  9. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 118
  10. 2024LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Modelscited by 98
  11. 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 97
  12. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learningcited by 94
38 more
  1. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 90
  2. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 85
  3. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 60
  4. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  5. 2022A Survey on Quantum Reinforcement Learningcited by 51
  6. 2021Learning to Select Cuts for Efficient Mixed-Integer Programmingcited by 48
  7. 2021Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approachcited by 46
  8. 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 44
  9. 2024A Scalable Communication Protocol for Networks of Large Language Modelscited by 44
  10. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  11. 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
  12. 2023Diffusion Model-Augmented Behavioral Cloningcited by 37
  13. 2024A review on data-driven constitutive laws for solidscited by 35
  14. 2021Independent Natural Policy Gradient Always Converges in Markov Potential Gamescited by 34
  15. 2022On Improving Cross-dataset Generalization of Deepfake Detectorscited by 34
  16. 2025Reinforced Lifelong Editing for Language Modelscited by 34
  17. 2025Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Explorationcited by 34
  18. 2021Learning Knowledge Graph-based World Models of Textual Environmentscited by 31
  19. 2021Data-Free Knowledge Transfer: A Surveycited by 31
  20. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agentscited by 31
  21. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 31
  22. 2022Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrievalcited by 27
  23. 2022Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Graspscited by 27
  24. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 27
  25. 2024SkillMimic: Learning Basketball Interaction Skills from Demonstrationscited by 27
  26. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  27. 2021Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environmentscited by 24
  28. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  29. 2023Creative Agents: Empowering Agents with Imagination for Creative Taskscited by 24
  30. 2021A Survey on Human-aware Robot Navigationcited by 23
  31. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 23
  32. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  33. 2025LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Modelscited by 23
  34. 2021An Overview and Experimental Study of Learning-based Optimization Algorithms for Vehicle Routing Problemcited by 22
  35. 2022FreeKD: Free-direction Knowledge Distillation for Graph Neural Networkscited by 22
  36. 2023Quantum Deep Hedgingcited by 22
  37. 2023Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Modelscited by 22
  38. 2024Learning to Watermark LLM-generated Text via Reinforcement Learningcited by 22

50 most cited of 466 All 466 (JSON)