mlsanityData to 7 Oct 2026

Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning

arXiv 1910.05396 ↗First posted 11 Oct 2019cs.LG stat.MLcited by 102

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we propose a simple technique to improve a generalization ability of deep RL agents by introducing a randomized (convolutional) neural network that randomly perturbs input observations. It enables trained agents to adapt to new domains by learning robust features invariant across varied and randomized environments. Furthermore, we consider an inference method based on the Monte Carlo approximation to reduce the variance induced by this randomization. We demonstrate the superiority of our method across 2D CoinRun, 3D DeepMind Lab exploration and 3D robotics control tasks: it significantly outperforms various regularization and data augmentation methods for the same purpose.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 23; 2023: 18; 2024: 14; 2025: 14; 2026: 3.

102 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 760
  2. 2021Domain Generalization with MixStylecited by 563
  3. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  4. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 127
  5. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  6. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  7. 2021Broaden Your Views for Self-Supervised Video Learningcited by 108
  8. 2021State Entropy Maximization with Random Encoders for Efficient Explorationcited by 107
  9. 2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 102
  10. 2022SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learningcited by 96
  11. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 81
  12. 2021Vision-Language Navigation with Random Environmental Mixupcited by 70
38 more
  1. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  2. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  3. 2022Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learningcited by 58
  4. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52
  5. 2021Adversarially Guided Actor-Criticcited by 47
  6. 2021SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policiescited by 42
  7. 2021MADE: Exploration via Maximizing Deviation from Explored Regionscited by 40
  8. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  9. 2022Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learningcited by 32
  10. 2022Chain of Thought Imitation with Procedure Cloningcited by 30
  11. 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 30
  12. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  13. 2022Continuous MDP Homomorphisms and Homomorphic Policy Gradientcited by 24
  14. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  15. 2023GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Mapscited by 23
  16. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  17. 2023Causal Reinforcement Learning: A Surveycited by 22
  18. 2022Mitigating Dataset Bias by Using Per-sample Gradientcited by 21
  19. 2023Explore to Generalize in Zero-Shot RLcited by 20
  20. 2021InsertionNet -- A Scalable Solution for Insertioncited by 15
  21. 2021Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentationcited by 15
  22. 2022Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributionscited by 15
  23. 2023MoVie: Visual Model-Based Policy Adaptation for View Generalizationcited by 15
  24. 2022Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racingcited by 13
  25. 2023Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractionscited by 13
  26. 2021Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixturecited by 12
  27. 2024Causal Action Influence Aware Counterfactual Data Augmentationcited by 12
  28. 2023Guide Your Agent with Adaptive Multimodal Rewardscited by 10
  29. 2022Local Feature Swapping for Generalization in Reinforcement Learningcited by 9
  30. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  31. 2025Gradient-Guided Annealing for Domain Generalizationcited by 9
  32. 2023Policy Gradient Methods in the Presence of Symmetries and State Abstractionscited by 8
  33. 2024A Survey Analyzing Generalization in Deep Reinforcement Learningcited by 8
  34. 2021Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environmentscited by 6
  35. 2025Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learningcited by 6
  36. 2023Task Aware Dreamer for Task Generalization in Reinforcement Learningcited by 5
  37. 2024Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidencecited by 5
  38. 2024Focus On What Matters: Separated Models For Visual-Based RL Generalizationcited by 5

50 most cited of 102 All 102 (JSON)