mlsanityData to 7 Oct 2026

DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck

arXiv 2102.13268 ↗First posted 26 Feb 2021cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning (DRL) agents are often sensitive to visual changes that were unseen in their training environments. To address this problem, we leverage the sequential nature of RL to learn robust representations that encode only task-relevant information from observations based on the unsupervised multi-view setting. Specifically, we introduce a novel contrastive version of the Multi-View Information Bottleneck (MIB) objective for temporal data. We train RL agents from pixels with this auxiliary objective to learn robust representations that can compress away task-irrelevant information and are predictive of task-relevant dynamics. This approach enables us to train high-performance policies that are robust to visual distractions and can generalize well to unseen environments. We demonstrate that our approach can achieve SOTA performance on a diverse set of visual control tasks in the DeepMind Control Suite when the background is replaced with natural videos. In addition, we show that our approach outperforms well-established baselines for generalization to unseen environments on the Procgen benchmark. Our code is open-sourced and available at https://github. com/BU-DEPEND-Lab/DRIBO.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 26 Feb 2021.

Builds on

36 of 51 references.

References · 36

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  5. 2017The Kinetics Human Action Video Datasetcited by 1,894
  6. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  7. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  8. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  9. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  10. 2016End to End Learning for Self-Driving Carscited by 1,000
  11. 2020Mastering Atari with Discrete World Modelscited by 990
  12. 2018DeepMind Control Suitecited by 935
24 more
  1. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  2. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  3. 2018MINE: Mutual Information Neural Estimationcited by 680
  4. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  5. 2019On Variational Bounds of Mutual Informationcited by 550
  6. 2020Reinforcement Learning with Augmented Datacited by 452
  7. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  8. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  9. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 266
  10. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 228
  11. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 189
  12. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 170
  13. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  14. 2018Generalization and Regularization in DQNcited by 117
  15. 2016A Survey of Multi-View Representation Learningcited by 107
  16. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 81
  17. 2020Deep Reinforcement and InfoMax Learningcited by 79
  18. 2020The Conditional Entropy Bottleneckcited by 75
  19. 2020Automatic Data Augmentation for Generalization in Deep Reinforcement Learningcited by 71
  20. 2020Predictive Information Accelerates Learning in RLcited by 56
  21. 2015From Pixels to Torques: Policy Learning with Deep Dynamical Modelscited by 44
  22. 2018Policy Transfer with Strategy Optimizationcited by 41
  23. 2018Natural Environment Benchmarks for Reinforcement Learningcited by 32
  24. 2019Multi-View Reinforcement Learningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 14; 2024: 5; 2025: 2; 2026: 2.

31 papers.

Sort:

By area:

  1. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  2. 2023PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learningcited by 42
  3. 2022Efficient Knowledge Distillation from Model Checkpointscited by 37
  4. 2022Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learningcited by 32
  5. 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 30
  6. 2023Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stagescited by 27
  7. 2023Behavior Contrastive Learning for Unsupervised Skill Discoverycited by 26
  8. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  9. 2021Learning Representations for Pixel-based Control: What Matters and Why?cited by 24
  10. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  11. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  12. 2025A Survey of State Representation Learning for Deep Reinforcement Learningcited by 17
19 more
  1. 2021SimSR: Simple Distance-based State Representation for Deep Reinforcement Learningcited by 14
  2. 2023Normalization Enhances Generalization in Visual Reinforcement Learningcited by 13
  3. 2024Reinforcement Learning with Generalizable Gaussian Splattingcited by 11
  4. 2023Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learningcited by 8
  5. 2023Bridging the Sim-to-Real Gap from the Information Bottleneck Perspectivecited by 8
  6. 2023Learning to Discover Skills through Guidancecited by 8
  7. 2023Generalization in Visual Reinforcement Learning with the Reward Sequence Distributioncited by 4
  8. 2024Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensorscited by 4
  9. 2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
  10. 2023Sequential Action-Induced Invariant Representation for Reinforcement Learningcited by 3
  11. 2022Tackling Visual Control via Multi-View Exploration Maximizationcited by 1
  12. 2024Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentationcited by 1
  13. 2024SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasetscited by 1
  14. 2024The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Datacited by 1
  15. 2025Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVscited by 1
  16. 2022Rollout Total Correlation for Deep Reinforcement Learningcited by 0
  17. 2023Robust Offline Reinforcement Learning -- Certify the Confidence Intervalcited by 0
  18. 2026Sparse Masked Attention Policies for Reliable Generalizationcited by 0
  19. 2026Moving Beyond More Views: Redundancy-Aware Ego-Exo Fusion for Proficiency Estimationcited by 0