mlsanityData to 7 Oct 2026

Domain Adversarial Reinforcement Learning

arXiv 2102.07097 ↗First posted 14 Feb 2021cs.LG cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e.g. when there are different backgrounds or change in contrast, brightness, etc. We assume that our agent has access to only a few of the MDPs from the MDP distribution during training. The performance of the agent is then reported on new unknown test domains drawn from the distribution (e.g. unseen backgrounds). For this "zero-shot RL" task, we enforce invariance of the learned representations to visual domains via a domain adversarial optimization process. We empirically show that this approach allows achieving a significant generalization improvement to new unseen domains.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 29 of its 31 references that are in the map. First posted on arXiv 14 Feb 2021.

Builds on

29 of 31 references.

References · 29

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  3. 2017The Kinetics Human Action Video Datasetcited by 1,894
  4. 2018World Modelscited by 1,444
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  6. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  7. 2018DeepMind Control Suitecited by 935
  8. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  9. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  10. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  11. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  12. 2020Reinforcement Learning with Augmented Datacited by 452
17 more
  1. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  2. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  3. 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 268
  4. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
  5. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 170
  6. 2019Provably efficient RL with Rich Observations via Latent State Decodingcited by 169
  7. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 124
  8. 2020Self-Supervised Policy Adaptation during Deploymentcited by 121
  9. 2020Invariant Causal Prediction for Block MDPscited by 104
  10. 2020Deep Reinforcement and InfoMax Learningcited by 79
  11. 2014Domain-Adversarial Neural Networkscited by 78
  12. 2018Combined Reinforcement Learning via Abstract Representationscited by 37
  13. 2018Natural Environment Benchmarks for Reinforcement Learningcited by 32
  14. 2019Robust Visual Domain Randomization for Reinforcement Learningcited by 13
  15. 2020Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-Based Robot Navigationcited by 13
  16. 2020Mutual Information Maximization for Robust Plannable Representationscited by 7
  17. 2020Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 7; 2024: 0; 2025: 4; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  2. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  3. 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learningcited by 27
  4. 2021Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLcited by 20
  5. 2023Explore to Generalize in Zero-Shot RLcited by 20
  6. 2022Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learningcited by 19
  7. 2022Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racingcited by 13
  8. 2025Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learningcited by 7
  9. 2022Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLcited by 4
  10. 2023Online Prototype Alignment for Few-shot Policy Transfercited by 4
  11. 2023Learning Generalizable Agents via Saliency-Guided Features Decorrelationcited by 3
  12. 2022Uniqueness and Complexity of Inverse MDP Modelscited by 2
7 more
  1. 2022Style-Agnostic Reinforcement Learningcited by 2
  2. 2023Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learningcited by 2
  3. 2025Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)cited by 2
  4. 2023VIBR: Learning View-Invariant Value Functions for Robust Visual Controlcited by 1
  5. 2025A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learningcited by 1
  6. 2025State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learningcited by 0
  7. 2026Reinforcement Learning from Cross-domain Videos with Video Prediction Modelcited by 0