mlsanityData to 7 Oct 2026

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

arXiv 1707.08475 ↗First posted 26 Jul 2017stat.ML cs.AI cs.LGcited by 147

Not on the map. Why?

Abstract (arXiv)

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain shifts - even with no access to the target domain. DARLA significantly outperforms conventional baselines in zero-shot domain adaptation scenarios, an effect that holds across a variety of RL environments (Jaco arm, DeepMind Lab) and base RL algorithms (DQN, A3C and EC).

Key facts. Cited by 147 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 37; 2022: 35; 2023: 28; 2024: 19; 2025: 20; 2026: 7.

147 papers.

Sort:

By area:

  1. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  2. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  3. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  4. 2021Learning Task Informed Abstractionscited by 58
  5. 2021Learning to See before Learning to Act: Visual Pre-training for Manipulationcited by 50
  6. 2022Visual Reinforcement Learning with Self-Supervised 3D Representationscited by 45
  7. 2021Learning Markov State Abstractions for Deep Reinforcement Learningcited by 42
  8. 2024Sharing Knowledge in Multi-Task Deep Reinforcement Learningcited by 42
  9. 2022Geometric Multimodal Contrastive Representation Learningcited by 40
  10. 2021Domain Adaptation In Reinforcement Learning Via Latent Unified State Representationcited by 33
  11. 2022Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learningcited by 32
  12. 2025Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentationcited by 31
38 more
  1. 2021On the Power of Multitask Representation Learning in Linear MDPcited by 30
  2. 2022Disentanglement with Biological Constraints: A Theory of Functional Cell Typescited by 30
  3. 2026Maximum Likelihood Reinforcement Learningcited by 29
  4. 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learningcited by 27
  5. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  6. 2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 25
  7. 2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
  8. 2023Causal Reinforcement Learning: A Surveycited by 22
  9. 2021Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLcited by 20
  10. 2021Solving Compositional Reinforcement Learning Problems via Task Reductioncited by 19
  11. 2022Abstraction for Deep Reinforcement Learningcited by 19
  12. 2022Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learningcited by 19
  13. 2022Transfer RL across Observation Feature Spaces via Model-Based Regularizationcited by 18
  14. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  15. 2021Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functionscited by 17
  16. 2025A Survey of State Representation Learning for Deep Reinforcement Learningcited by 17
  17. 2022Nearly Minimax Algorithms for Linear Bandits with Shared Representationcited by 16
  18. 2021Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learningcited by 15
  19. 2021Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learningcited by 15
  20. 2021Certifiably Robust Variational Autoencoderscited by 14
  21. 2021Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Modelcited by 14
  22. 2022NovGrid: A Flexible Grid World for Evaluating Agent Response to Noveltycited by 14
  23. 2021Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddingscited by 12
  24. 2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
  25. 2022Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixelscited by 12
  26. 2023Combining Behaviors with the Successor Features Keyboardcited by 12
  27. 2022Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisationcited by 11
  28. 2022Learn the Time to Learn: Replay Scheduling in Continual Learningcited by 11
  29. 2023Aligning Robot and Human Representationscited by 11
  30. 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
  31. 2021DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunitiescited by 10
  32. 2022Alleviating Adversarial Attacks on Variational Autoencoders with MCMCcited by 10
  33. 2023Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RLcited by 10
  34. 2024Simplifying Latent Dynamics with Softly State-Invariant World Modelscited by 10
  35. 2022Local Feature Swapping for Generalization in Reinforcement Learningcited by 9
  36. 2024iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learningcited by 9
  37. 2021Disentanglement and Generalization Under Correlation Shiftscited by 8
  38. 2023DAVA: Disentangling Adversarial Variational Autoencodercited by 8

50 most cited of 147 All 147 (JSON)