Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning

• URL: http://arxiv.org/abs/2605.08202v1
• Date: Wed, 06 May 2026 01:21:53 GMT
• Title: Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
• Abstract summary: We propose DOSER (Diffusion-based OOD Detection and Selective Regularization), a novel framework that goes beyond uniform penalization.<n>We show that DOSER consistently attains superior performance to prior methods, especially on suboptimal datasets.
• Score: 29.019573695533563
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Offline reinforcement learning (RL) faces a critical challenge of overestimating the value of out-of-distribution (OOD) actions. Existing methods mitigate this issue by penalizing unseen samples, yet they fail to accurately identify OOD actions and may suppress beneficial exploration beyond the behavioral support. Although several methods have been proposed to differentiate OOD samples with distinct properties, they typically rely on restrictive assumptions about the data distribution and remain limited in discrimination ability. To address this problem, we propose DOSER (Diffusion-based OOD Detection and Selective Regularization), a novel framework that goes beyond uniform penalization. DOSER trains two diffusion models to capture the behavior policy and state distribution, using single-step denoising reconstruction error as a reliable OOD indicator. During policy optimization, it further distinguishes between beneficial and detrimental OOD actions by evaluating predicted transitions, selectively suppressing risky actions while encouraging exploration of high-potential ones. Theoretically, we prove that DOSER is a $γ$-contraction and therefore admits a unique fixed point with bounded value estimates. We further provide an asymptotic performance guarantee relative to the optimal policy under model approximation and OOD detection errors. Across extensive offline RL benchmarks, DOSER consistently attains superior performance to prior methods, especially on suboptimal datasets.

Related papers

• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs [35.326974180503065]
  We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs)<n>Motivated by recent findings on polysemanticity and redundancy in LLMs, we hypothesize that in-domain inputs exhibit higher dropout tolerance than OOD inputs.<n>We aggregate dropout tolerance across multiple layers via a valid ensemble approach, improving detection while maintaining theoretical false alarm bounds from ICAD.
  arXiv  Detail & Related papers  (2025-09-04T20:50:51Z)
• Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization [23.817251267022847]
  We propose the Behavior-Supported Policy Optimization (BSPO) method to mitigate the reward over-optimization issue.<n>BSPO reduces the generation of OOD responses during the reinforcement learning process.<n> Empirical results show that BSPO outperforms baselines in preventing reward over-optimization.
  arXiv  Detail & Related papers  (2025-03-23T16:20:59Z)
• Margin-bounded Confidence Scores for Out-of-Distribution Detection [2.373572816573706]
  We propose a novel method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem. MaCS enlarges the disparity between ID and OOD scores, which in turn makes the decision boundary more compact. Experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-09-22T05:40:25Z)
• Model-free Test Time Adaptation for Out-Of-Distribution Detection [62.49795078366206]
  We propose a Non-Parametric Test Time textbfAdaptation framework for textbfDistribution textbfDetection (abbr) abbr utilizes online test samples for model adaptation during testing, enhancing adaptability to changing data distributions. We demonstrate the effectiveness of abbr through comprehensive experiments on multiple OOD detection benchmarks.
  arXiv  Detail & Related papers  (2023-11-28T02:00:47Z)
• LINe: Out-of-Distribution Detection by Leveraging Important Neurons [15.797257361788812]
  We introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data. We propose a novel method, Leveraging Important Neurons (LINe), for post-hoc Out of distribution detection.
  arXiv  Detail & Related papers  (2023-03-24T13:49:05Z)
• Anti-Exploration by Random Network Distillation [63.04360288089277]
  We show that a naive choice of conditioning for the Random Network Distillation (RND) is not discriminative enough to be used as an uncertainty estimator. We show that this limitation can be avoided with conditioning based on Feature-wise Linear Modulation (FiLM) We evaluate it on the D4RL benchmark, showing that it is capable of achieving performance comparable to ensemble-based methods and outperforming ensemble-free approaches by a wide margin.
  arXiv  Detail & Related papers  (2023-01-31T13:18:33Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• How to Enable Uncertainty Estimation in Proximal Policy Optimization [20.468991996052953]
  Existing uncertainty estimation techniques have not seen widespread adoption in on-policy deep RL. We propose definitions of uncertainty and OOD for Actor-Critic RL algorithms. We show experimentally that the recently proposed method of Masksembles strikes a favourable balance among the survey methods.
  arXiv  Detail & Related papers  (2022-10-07T15:56:59Z)
• Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning [125.8224674893018]
  Offline Reinforcement Learning (RL) aims to learn policies from previously collected datasets without exploring the environment. Applying off-policy algorithms to offline RL usually fails due to the extrapolation error caused by the out-of-distribution (OOD) actions. We propose Pessimistic Bootstrapping for offline RL (PBRL), a purely uncertainty-driven offline algorithm without explicit policy constraints.
  arXiv  Detail & Related papers  (2022-02-23T15:27:16Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)

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.