mlsanityData to 14 Oct 2026

MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning

arXiv 2504.04164 ↗First posted 5 Apr 2025cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Existing visual model-based reinforcement learning (MBRL) algorithms with observation reconstruction often suffer from information conflicts, making it difficult to learn compact representations and hence result in less robust policies, especially in the presence of task-irrelevant visual distractions. In this paper, we first reveal that the information conflicts in current visual MBRL algorithms stem from visual representation learning and latent dynamics modeling with an information-theoretic perspective. Based on this finding, we present a new algorithm to resolve information conflicts for visual MBRL, named MInCo, which mitigates information conflicts by leveraging negative-free contrastive learning, aiding in learning invariant representation and robust policies despite noisy observations. To prevent the dominance of visual representation learning, we introduce time-varying reweighting to bias the learning towards dynamics modeling as training proceeds. We evaluate our method on several robotic control tasks with dynamic background distractions. Our experiments demonstrate that MInCo learns invariant representations against background noise and consistently outperforms current state-of-the-art visual MBRL methods. Code is available at https://github.com/ShiguangSun/minco.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 60 of its 84 references that are in the map. First posted on arXiv 5 Apr 2025.

Builds on

60 of 84 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Learning Latent Dynamic Robust Representations for World Models10 May

Other references · 59

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  12. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
38 more
  1. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  2. 2018World Modelscited by 1,513
  3. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  4. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  5. 2023Mastering Diverse Domains through World Modelscited by 1,253
  6. 2020Mastering Atari with Discrete World Modelscited by 1,007
  7. 2018DeepMind Control Suitecited by 956
  8. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  10. 2020Contrastive Learning with Hard Negative Samplescited by 628
  11. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 585
  12. 2019On Variational Bounds of Mutual Informationcited by 559
  13. 2019Model-Based Reinforcement Learning for Ataricited by 502
  14. 2020Reinforcement Learning with Augmented Datacited by 468
  15. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  16. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  17. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 372
  18. 2020Debiased Contrastive Learningcited by 356
  19. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  20. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
  21. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 274
  22. 2020Decoupling Representation Learning from Reinforcement Learningcited by 269
  23. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 260
  24. 2022Masked Visual Pre-training for Motor Controlcited by 248
  25. 2021Mastering Atari Games with Limited Datacited by 237
  26. 2018Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Controlcited by 230
  27. 2018Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansioncited by 168
  28. 2018Model-Based Value Estimation for Efficient Model-Free Reinforcement Learningcited by 156
  29. 2019Deep Reinforcement Learning for Cyber Securitycited by 95
  30. 2020Offline Reinforcement Learning from Images with Latent Space Modelscited by 95
  31. 2021DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representationscited by 74
  32. 2022Denoised MDPs: Learning World Models Better Than the World Itselfcited by 68
  33. 2020Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstructioncited by 66
  34. 2021Learning Task Informed Abstractionscited by 58
  35. 2022Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Modelscited by 53
  36. 2021Incremental False Negative Detection for Contrastive Learningcited by 48
  37. 2021Solving Inefficiency of Self-supervised Representation Learningcited by 41
  38. 2022Mask-based Latent Reconstruction for Reinforcement Learningcited by 39

50 most cited of 59 All 59 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Self-Consistent Model-based Adaptation for Visual Reinforcement Learning
  2. 2025Pre-trained Visual Representations Generalize Where it Matters in Model-Based Reinforcement Learning
  3. 2024The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
  4. 2026VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
  5. 2025Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning
  6. 2026Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
  7. 2022Masked World Models for Visual Control
  8. 2024DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors