mlsanityData to 7 Oct 2026

VIBR: Learning View-Invariant Value Functions for Robust Visual Control

arXiv 2306.08537 ↗First posted 14 Jun 2023cs.LG cs.CV cs.SYcited by 1

Not on the map. Why?

Abstract (arXiv)

End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while representation learning methods use auxiliary losses to learn task-relevant features. Yet, reinforcement still struggles in visually diverse environments full of distractions and spurious noise. In this work, we tackle the problem of robust visual control at its core and present VIBR (View-Invariant Bellman Residuals), a method that combines multi-view training and invariant prediction to reduce out-of-distribution (OOD) generalization gap for RL based visuomotor control. Our model-free approach improve baselines performances without the need of additional representation learning objectives and with limited additional computational cost. We show that VIBR outperforms existing methods on complex visuo-motor control environment with high visual perturbation. Our approach achieves state-of the-art results on the Distracting Control Suite benchmark, a challenging benchmark still not solved by current methods, where we evaluate the robustness to a number of visual perturbators, as well as OOD generalization and extrapolation capabilities.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 50 references that are in the map. First posted on arXiv 14 Jun 2023.

Builds on

45 of 50 references.

References · 45

  1. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  4. 2019Invariant Risk Minimizationcited by 1,832
  5. 2018On the Spectral Bias of Neural Networkscited by 1,321
  6. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  7. 2018DeepMind Control Suitecited by 935
  8. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  10. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  11. 2019Solving Rubik's Cube with a Robot Handcited by 699
  12. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
33 more
  1. 2021Domain Generalization with MixStylecited by 563
  2. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  3. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  4. 2020Reinforcement Learning with Augmented Datacited by 452
  5. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  6. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 400
  7. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  8. 2020Data-Efficient Reinforcement Learning with Self-Predictive Representationscited by 309
  9. 2022Masked Visual Pre-training for Motor Controlcited by 246
  10. 2022The Primacy Bias in Deep Reinforcement Learningcited by 242
  11. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  12. 2019Provably efficient RL with Rich Observations via Latent State Decodingcited by 169
  13. 2022Masked World Models for Visual Controlcited by 169
  14. 2020Acme: A Research Framework for Distributed Reinforcement Learningcited by 146
  15. 2020Generalization in Reinforcement Learning by Soft Data Augmentationcited by 132
  16. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  17. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  18. 2020Invariant Causal Prediction for Block MDPscited by 104
  19. 2019Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learningcited by 102
  20. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 97
  21. 2020Improving Generalization in Reinforcement Learning with Mixture Regularizationcited by 81
  22. 2022Denoised MDPs: Learning World Models Better Than the World Itselfcited by 66
  23. 2020The Value-Improvement Path: Towards Better Representations for Reinforcement Learningcited by 60
  24. 2020Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentationcited by 57
  25. 2019A Geometric Perspective on Optimal Representations for Reinforcement Learningcited by 54
  26. 2020Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learningcited by 37
  27. 2020Measuring Visual Generalization in Continuous Control from Pixelscited by 20
  28. 2021Domain Adversarial Reinforcement Learningcited by 19
  29. 2021Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentationcited by 15
  30. 2020Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Criticcited by 12
  31. 2020Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillationcited by 10
  32. 2020Intervention Design for Effective Sim2Real Transfercited by 9
  33. 2022Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Diagnosing JEPA World Models with Action-Conditioned Predictive Consistencycited by 2