mlsanityData to 7 Oct 2026

Transfer Learning in Deep Reinforcement Learning: A Survey

arXiv 2009.07888 ↗First posted 16 Sep 2020cs.LG cs.AI stat.MLcited by 259

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the promising prospects of reinforcement learning in numerous domains such as robotics and game-playing, transfer learning has arisen to tackle various challenges faced by reinforcement learning, by transferring knowledge from external expertise to facilitate the efficiency and effectiveness of the learning process. In this survey, we systematically investigate the recent progress of transfer learning approaches in the context of deep reinforcement learning. Specifically, we provide a framework for categorizing the state-of-the-art transfer learning approaches, under which we analyze their goals, methodologies, compatible reinforcement learning backbones, and practical applications. We also draw connections between transfer learning and other relevant topics from the reinforcement learning perspective and explore their potential challenges that await future research progress.

Key facts. Cited by 259 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 41; 2023: 65; 2024: 58; 2025: 46; 2026: 18.

259 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 166
  3. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  4. 2023Large Language Models for Robotics: A Surveycited by 132
  5. 2022Head2Toe: Utilizing Intermediate Representations for Better Transfer Learningcited by 83
  6. 2021Distributed Deep Learning in Open Collaborationscited by 58
  7. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 58
  8. 2024FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuningcited by 54
  9. 2023Learning from models beyond fine-tuningcited by 47
  10. 2021AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learningcited by 46
  11. 2024RS-Agent: Automating Remote Sensing Tasks through Intelligent Agentcited by 46
  12. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
38 more
  1. 2022Provable Benefits of Representational Transfer in Reinforcement Learningcited by 38
  2. 2022Disentangling Transfer in Continual Reinforcement Learningcited by 31
  3. 2021Block Contextual MDPs for Continual Learningcited by 25
  4. 2024SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learningcited by 24
  5. 2025The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutionscited by 24
  6. 2023Causal Reinforcement Learning: A Surveycited by 22
  7. 2021Transfer Learning for Future Wireless Networks: A Comprehensive Surveycited by 18
  8. 2022Transfer RL across Observation Feature Spaces via Model-Based Regularizationcited by 18
  9. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 17
  10. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17
  11. 2021Provably Efficient Multi-Task Reinforcement Learning with Model Transfercited by 16
  12. 2025A Survey of Continual Reinforcement Learningcited by 16
  13. 2022State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersectionscited by 15
  14. 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitationcited by 15
  15. 2025Out-of-Distribution Generalization in Time Series: A Surveycited by 15
  16. 2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
  17. 2022NovGrid: A Flexible Grid World for Evaluating Agent Response to Noveltycited by 14
  18. 2022Robots Enact Malignant Stereotypescited by 14
  19. 2023Neuro-Symbolic World Models for Adapting to Open World Noveltycited by 14
  20. 2023Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPscited by 14
  21. 2025General agents contain world modelscited by 14
  22. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  23. 2021A New Representation of Successor Features for Transfer across Dissimilar Environmentscited by 13
  24. 2021Can Q-Learning be Improved with Advice?cited by 13
  25. 2023A Domain-Agnostic Approach for Characterization of Lifelong Learning Systemscited by 13
  26. 2022Training Mixed-Domain Translation Models via Federated Learningcited by 12
  27. 2023Automated Design of Metaheuristic Algorithms: A Surveycited by 12
  28. 2023Combining Behaviors with the Successor Features Keyboardcited by 12
  29. 2023Fast Policy Learning for Linear Quadratic Control with Entropy Regularizationcited by 11
  30. 2024Large Language Models as Agents in Two-Player Gamescited by 10
  31. 2024Toward Enhanced Reinforcement Learning-Based Resource Management via Digital Twin: Opportunities, Applications, and Challengescited by 10
  32. 2025MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attackscited by 10
  33. 2022Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methodscited by 9
  34. 2023Towards practical reinforcement learning for tokamak magnetic controlcited by 9
  35. 2023A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learningcited by 9
  36. 2021General Board Game Conceptscited by 8
  37. 2023AutoRL Hyperparameter Landscapescited by 8
  38. 2023Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrationscited by 8

50 most cited of 259 All 259 (JSON)