paper-with-me

홈 › Papers

How Hard is it to Confuse a World Model?

2025-10-24 · Waris Radji, Odalric-Ambrym Maillard arxiv

In reinforcement learning (RL) theory, the concept of most confusing instances is central to establishing regret lower bounds, that is, the minimal exploration needed to solve a problem. Given a reference model and its optimal policy, a most confusing instance is the statistically closest alternative model that makes a suboptimal policy optimal. While this concept is well-studied in multi-armed bandits and ergodic tabular Markov decision processes, constructing such instances remains an open question in the general case. In this paper, we formalize this problem for neural network world models as a constrained optimization: finding a modified model that is statistically close to the reference one, while producing divergent performance between optimal and suboptimal policies. We propose an adversarial training procedure to solve this problem and conduct an empirical study across world models of varying quality. Our results suggest that the degree of achievable confusion correlates with uncertainty in the approximate model, which may inform theoretically-grounded exploration strategies for deep model-based RL.

📄 PDF Abstract BibTeX arXiv:2510.21232

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningMulti-Armed Bandits

Similar Papers 제목 키워드 기반

Towards Generalizable Medical Image Segmentation with Pixel-wise Uncertainty Estimation

2023-05-13 · Shuai Wang, Zipei Yan, Daoan Zhang, Zhongsen Li 외

Deep neural networks (DNNs) achieve promising performance in visual recognition under the independent and identically distributed (IID) hypothesis. In contrast, the IID hypothesis is not universally guaranteed in numerou…

Image SegmentationMedical Image AnalysisMedical Image SegmentationSemantic Segmentation

Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering

2019-01-22 · Binghui Chen, Weihong Deng

Deep metric learning has been widely applied in many computer vision tasks, and recently, it is more attractive in \emph{zero-shot image retrieval and clustering}(ZSRC) where a good embedding is requested such that the u…

ClusteringImage RetrievalMetric LearningRetrieval+1

U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning

2026-05-04 · Christine P Lee, Xinyu Jessica Wang, Aws Albarghouthi, David Porfirio 외 arxiv

LLMs are increasingly used for end-user task planning, yet their black-box nature limits users' ability to ensure reliability and control. While recent systems incorporate verification techniques, it remains unclear how …

Physical Adversarial Textures that Fool Visual Object Tracking

2019-04-24 · ICCV 2019 10 · Rey Reza Wiyatno, Anqi Xu

We present a system for generating inconspicuous-looking textures that, when displayed in the physical world as digital or printed posters, cause visual object tracking systems to become confused. For instance, as a targ…

ObjectObject TrackingVisual Object Tracking

Batch Group Normalization

2020-12-04 · Xiao-Yun Zhou, Jiacheng Sun, Nanyang Ye, Xu Lan 외

Deep Convolutional Neural Networks (DCNNs) are hard and time-consuming to train. Normalization is one of the effective solutions. Among previous normalization methods, Batch Normalization (BN) performs well at medium and…

Domain AdaptationFew-Shot LearningGPUimage-classification+3