Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift

• URL: http://arxiv.org/abs/2604.27411v1
• Date: Thu, 30 Apr 2026 04:28:02 GMT
• Title: Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
• Abstract summary: We study ways of responding to shift, including planning penalties, direct fine-tuning, global residual correction, and coarse gating.<n>Based on these negative results, we propose JEPA-Indexed Local Expert Growth.<n>The method uses a frozen JEPA representation only for problem indexing, while cluster-specific residual experts add local action corrections on top of the original controller.
• Score: 2.233624388203003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual model-based reinforcement learning (MBRL) agents can perform well on the training distribution, but often break down once the test environment shifts. In visual MBRL, recognizing that a shift has occurred is often the easier part; the harder part is turning that recognition into useful action-level correction. We study several ways of responding to shift, including planning penalties, direct fine-tuning, global residual correction, and coarse gating. In our experiments, these approaches either do not improve closed-loop control or hurt in-distribution (ID) performance. Based on these negative results, we propose JEPA-Indexed Local Expert Growth. The method uses a frozen JEPA representation only for problem indexing, while cluster-specific residual experts add local action corrections on top of the original controller. The baseline controller itself is not modified. Using paired-bootstrap evaluation, we find that the original naive-preference variant is not stable under stricter testing. In contrast, the harder-pair variant produces statistically significant OOD improvements on all four evaluated shift conditions while preserving ID performance. The learned experts also remain useful when the same shift is encountered again, which supports the view of adaptation as incremental knowledge growth rather than repeated full retraining. We further show that automatic ID rejection can be achieved with simple density models, whereas fine-grained discrimination among OOD sub-families is limited by the representation. Overall, the results indicate that, for visual MBRL under distribution shift, the main challenge is not simply noticing that the environment has changed, but applying the right local action correction after the change has been recognized.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift [47.77477373749725]
  We introduce a geometry aware framework that progressively discovers shifted data by leveraging the local manifold structure of visual features.<n>Our approach transfers robustly across different types of shifts, demonstrating strong generalization capabilities.
  arXiv  Detail & Related papers  (2026-05-29T11:55:31Z)
• Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation [52.620992698137236]
  Open-set test-time adaptation (OSTTA) addresses the challenge of adapting models to new environments.<n>In this paper, we first analyze the limitations of entropy in OSTTA and then introduce an angular loss to regulate feature norm magnitudes.<n>Our method achieves strong OOD detection while maintaining high ID classification performance.
  arXiv  Detail & Related papers  (2026-04-02T04:00:57Z)
• Online Bayesian Imbalanced Learning with Bregman-Calibrated Deep Networks [0.7106986689736825]
  We present textitOnline Bayesian Imbalanced Learning (OBIL), a principled framework that decouples likelihood-ratio estimation from class-prior assumptions.<n>Our approach builds on the established connection between Bregman divergences and proper scoring rules to show that deep networks trained with such losses produce posterior probability estimates.<n>We prove that these likelihood-ratio estimates remain valid under arbitrary changes in class priors and cost structures, requiring only a threshold adjustment for optimal Bayes decisions.
  arXiv  Detail & Related papers  (2026-02-08T21:23:00Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• Federated Learning with Sample-level Client Drift Mitigation [15.248811557566128]
  Federated Learning suffers from severe performance degradation due to data heterogeneity among clients.<n>We propose FedBSS that first mitigates the heterogeneity issue in a sample-level manner.<n>We also achieved effective results on feature distribution and noise label dataset setting.
  arXiv  Detail & Related papers  (2025-01-20T09:44:07Z)
• Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach [51.012396632595554]
  Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments. Recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. We develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects.
  arXiv  Detail & Related papers  (2023-12-15T12:58:05Z)
• Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks [86.42889611784855]
  normalization methods increase the vulnerability with respect to noise and input corruptions. We propose an unsupervised non-parametric distribution correction method that adapts the activation distribution of each layer. In our experiments, we empirically show that the proposed method effectively reduces the impact of intense image corruptions.
  arXiv  Detail & Related papers  (2021-10-05T11:36:25Z)
• Detecting Rewards Deterioration in Episodic Reinforcement Learning [63.49923393311052]
  In many RL applications, once training ends, it is vital to detect any deterioration in the agent performance as soon as possible. We consider an episodic framework, where the rewards within each episode are not independent, nor identically-distributed, nor Markov. We define the mean-shift in a way corresponding to deterioration of a temporal signal (such as the rewards), and derive a test for this problem with optimal statistical power.
  arXiv  Detail & Related papers  (2020-10-22T12:45:55Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.