mlsanityData to 14 Oct 2026

A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization

arXiv 2202.08444 ↗First posted 17 Feb 2022cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement Learning (DRL) aims to create intelligent agents that can learn to solve complex problems efficiently in a real-world environment. Typically, two learning goals: adaptation and generalization are used for baselining DRL algorithm's performance on different tasks and domains. This paper presents a survey on the recent developments in DRL-based approaches for adaptation and generalization. We begin by formulating these goals in the context of task and domain. Then we review the recent works under those approaches and discuss future research directions through which DRL algorithms' adaptability and generalizability can be enhanced and potentially make them applicable to a broad range of real-world problems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 58 of its 126 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

58 of 126 references.

References · 58

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  6. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  7. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  8. 2016End to End Learning for Self-Driving Carscited by 1,009
  9. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  10. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  11. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  12. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
38 more
  1. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  2. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  3. 2019Model-Based Reinforcement Learning for Ataricited by 502
  4. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
  5. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  6. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  7. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 455
  8. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 397
  9. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  10. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  11. 2019Dynamics-Aware Unsupervised Discovery of Skillscited by 313
  12. 2019Challenges of Real-World Reinforcement Learningcited by 291
  13. 2019Causal Confusion in Imitation Learningcited by 288
  14. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  15. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  16. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  17. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 157
  18. 2021Offline RL Without Off-Policy Evaluationcited by 151
  19. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 149
  20. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 131
  21. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 130
  22. 2018Variational Option Discovery Algorithmscited by 122
  23. 2020Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skillscited by 122
  24. 2020Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimizationcited by 120
  25. 2018Near-Optimal Representation Learning for Hierarchical Reinforcement Learningcited by 110
  26. 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 101
  27. 2020Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learningcited by 98
  28. 2020COG: Connecting New Skills to Past Experience with Offline Reinforcement Learningcited by 83
  29. 2018Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RLcited by 81
  30. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
  31. 2018Latent Space Policies for Hierarchical Reinforcement Learningcited by 67
  32. 2019Learning Reward Functions by Integrating Human Demonstrations and Preferencescited by 64
  33. 2021Hierarchical Reinforcement Learning By Discovering Intrinsic Optionscited by 58
  34. 2019ES-MAML: Simple Hessian-Free Meta Learningcited by 57
  35. 2018Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddingscited by 52
  36. 2019Meta Reinforcement Learning for Sim-to-real Domain Adaptationcited by 49
  37. 2020Sim2Real Transfer for Reinforcement Learning without Dynamics Randomizationcited by 47
  38. 2020Meta-Learning through Hebbian Plasticity in Random Networkscited by 47

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24