mlsanityData to 7 Oct 2026

Reinforcement Learning with Augmented Data

arXiv 2004.14990 ↗First posted 30 Apr 2020cs.LG stat.MLcited by 452

Not on the map. Why?

Cited by 67 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) data-efficiency of learning and (b) generalization to new environments. To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. We perform the first extensive study of general data augmentations for RL on both pixel-based and state-based inputs, and introduce two new data augmentations - random translate and random amplitude scale. We show that augmentations such as random translate, crop, color jitter, patch cutout, random convolutions, and amplitude scale can enable simple RL algorithms to outperform complex state-of-the-art methods across common benchmarks. RAD sets a new state-of-the-art in terms of data-efficiency and final performance on the DeepMind Control Suite benchmark for pixel-based control as well as OpenAI Gym benchmark for state-based control. We further demonstrate that RAD significantly improves test-time generalization over existing methods on several OpenAI ProcGen benchmarks. Our RAD module and training code are available at https://www.github.com/MishaLaskin/rad.

Key facts. Cited by 452 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 87; 2022: 92; 2023: 101; 2024: 68; 2025: 63; 2026: 40.

452 papers.

Sort:

By area:

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2023Mastering Diverse Domains through World Modelscited by 1,193
  3. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  4. 2021Domain Generalization: A Surveycited by 760
  5. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  6. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  7. 2021Domain Generalization with MixStylecited by 563
  8. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  9. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  10. 2022Masked Visual Pre-training for Motor Controlcited by 246
  11. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  12. 2021Mastering Atari Games with Limited Datacited by 235
38 more
  1. 2021Reinforcement Learning with Prototypical Representationscited by 179
  2. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  3. 2022Masked World Models for Visual Controlcited by 169
  4. 2023Language-Driven Representation Learning for Roboticscited by 163
  5. 2022The Unsurprising Effectiveness of Pre-Trained Vision Models for Controlcited by 155
  6. 2023Bigger, Better, Faster: Human-level Atari with human-level efficiencycited by 145
  7. 2021URLB: Unsupervised Reinforcement Learning Benchmarkcited by 138
  8. 2023Transformer-based World Models Are Happy With 100k Interactionscited by 137
  9. 2021Goal-Conditioned Reinforcement Learning with Imagined Subgoalscited by 129
  10. 2024THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulationcited by 128
  11. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  12. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learningcited by 114
  13. 2021State Entropy Maximization with Random Encoders for Efficient Explorationcited by 107
  14. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 107
  15. 2021B-Pref: Benchmarking Preference-Based Reinforcement Learningcited by 106
  16. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 104
  17. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 101
  18. 2023Synthetic Experience Replaycited by 100
  19. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 97
  20. 2022SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learningcited by 96
  21. 2020Offline Reinforcement Learning from Images with Latent Space Modelscited by 94
  22. 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentationcited by 86
  23. 2021S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningcited by 85
  24. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 84
  25. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 81
  26. 2023Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulationcited by 78
  27. 2023Contrastive Preference Learning: Learning from Human Feedback without RLcited by 77
  28. 2022Offline Visual Representation Learning for Embodied Navigationcited by 74
  29. 2021DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representationscited by 73
  30. 2021Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformerscited by 71
  31. 2022CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learningcited by 70
  32. 2022CIC: Contrastive Intrinsic Control for Unsupervised Skill Discoverycited by 66
  33. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  34. 2022Denoised MDPs: Learning World Models Better Than the World Itselfcited by 66
  35. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 64
  36. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  37. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 63
  38. 2022Challenges and Opportunities in Offline Reinforcement Learning from Visual Observationscited by 63

50 most cited of 452 All 452 (JSON)