English
Related papers

Related papers: Distributional Reinforcement Learning with Informa…

200 papers

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-06 Thomas Bouvier , Bogdan Nicolae , Hugo Chaugier , Alexandru Costan , Ian Foster , Gabriel Antoniu

Reinforcement learning (RL) for reachability specifications is fundamental in sequential decision-making, yet theoretical guarantees remain less explored. A recent work achieves asymptotic convergence to optimal policies. However, this…

Machine Learning · Computer Science 2026-05-26 Amogh Palasamudram , Jakub Svoboda , Suguman Bansal , Krishnendu Chatterjee

A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems. Verification approaches centered around reachability analysis fail to scale, and purely statistical approaches…

Artificial Intelligence · Computer Science 2025-03-11 Souradeep Dutta , Michele Caprio , Vivian Lin , Matthew Cleaveland , Kuk Jin Jang , Ivan Ruchkin , Oleg Sokolsky , Insup Lee

The Information Bottleneck (IB) method frequently suffers from unstable optimization, characterized by abrupt representation shifts near critical points of the IB trade-off parameter, beta. In this paper, I introduce a novel approach to…

Machine Learning · Computer Science 2025-05-15 Faruk Alpay

The robustness of Unmanned Surface Vehicles (USV) is crucial when facing unknown and complex marine environments, especially when heteroscedastic observational noise poses significant challenges to sensor-based navigation tasks. Recently,…

Robotics · Computer Science 2025-12-02 Zhaofan Zhang , Minghao Yang , Sihong Xie , Hui Xiong

Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous…

Machine Learning · Computer Science 2023-05-01 Yilin Lyu , Xin Liu , Mingyang Song , Xinyue Wang , Yaxin Peng , Tieyong Zeng , Liping Jing

Leveraging high-quality joint representations from multimodal data can greatly enhance model performance in various machine-learning based applications. Recent multimodal learning methods, based on the multimodal information bottleneck…

Machine Learning · Computer Science 2025-05-27 Qilong Wu , Yiyang Shao , Jun Wang , Xiaobo Sun

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Machine Learning · Computer Science 2025-11-12 Debamita Ghosh , George K. Atia , Yue Wang

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First,…

Machine Learning · Computer Science 2020-08-10 Rana Ali Amjad , Bernhard C. Geiger

We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We…

Machine Learning · Computer Science 2019-12-19 Charlie Frogner , Sebastian Claici , Edward Chien , Justin Solomon

We propose a novel framework to solve risk-sensitive reinforcement learning (RL) problems where the agent optimises time-consistent dynamic spectral risk measures. Based on the notion of conditional elicitability, our methodology constructs…

Machine Learning · Computer Science 2023-05-02 Anthony Coache , Sebastian Jaimungal , Álvaro Cartea

We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed algorithm, $\textit{Calibrated Evidential…

Machine Learning · Computer Science 2024-06-05 Alex Christopher Stutts , Danilo Erricolo , Theja Tulabandhula , Amit Ranjan Trivedi

Offline reinforcement learning aims to learn from pre-collected datasets without active exploration. This problem faces significant challenges, including limited data availability and distributional shifts. Existing approaches adopt a…

Machine Learning · Computer Science 2024-10-01 Yue Wang , Jinjun Xiong , Shaofeng Zou

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

Robotics · Computer Science 2022-05-10 Hirotaka Tahara , Hikaru Sasaki , Hanbit Oh , Brendan Michael , Takamitsu Matsubara

Branch-and-bound is a systematic enumerative method for combinatorial optimization, where the performance highly relies on the variable selection strategy. State-of-the-art handcrafted heuristic strategies suffer from relatively slow…

Machine Learning · Computer Science 2022-06-15 Tianyu Zhang , Amin Banitalebi-Dehkordi , Yong Zhang

The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenges that exist at the algorithmic level. With growing interest…

Machine Learning · Computer Science 2025-03-04 Behraj Khan , Behroz Mirza , Nouman Durrani , Tahir Syed

The information bottleneck framework provides a systematic approach to learning representations that compress nuisance information in the input and extract semantically meaningful information about predictions. However, the choice of a…

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently…

Machine Learning · Computer Science 2025-12-12 Yi Huang , Qingyun Sun , Yisen Gao , Haonan Yuan , Xingcheng Fu , Jianxin Li

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha