paper-with-me

Papers

Learning under Invariable Bayesian Safety

2020-06-08 · Gal Bahar, Omer Ben-Porat, Kevin Leyton-Brown, Moshe Tennenholtz

A recent body of work addresses safety constraints in explore-and-exploit systems. Such constraints arise where, for example, exploration is carried out by individuals whose welfare should be balanced with overall welfare. In this paper, we adopt a model inspired by recent work on a bandit-like setting for recommendations. We contribute to this line of literature by introducing a safety constraint that should be respected in every round and determines that the expected value in each round is above a given threshold. Due to our modeling, the safe explore-and-exploit policy deserves careful planning, or otherwise, it will lead to sub-optimal welfare. We devise an asymptotically optimal algorithm for the setting and analyze its instance-dependent convergence rate.

📄 PDF Abstract BibTeX arXiv:2006.04497

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Consistent Assistant Domains Transformer for Source-free Domain Adaptation

2025-10-02 · Renrong Shao, Wei Zhang, Kangyang Luo, Qin Li 외 arxiv

Source-free domain adaptation (SFDA) aims to address the challenge of adapting to a target domain without accessing the source domain directly. However, due to the inaccessibility of source domain data, deterministic inv…

Source-Free Domain Adaptation

Quantitative Metrics for Benchmarking Human-Aware Robot Navigation

2023-07-26 · IEEE Access 2023 7 · Jarosław Karwowski, Wojciech Szynkiewicz

Social robots have recently gained popularity, and many human-aware navigation approaches have emerged. This work presents a comprehensive benchmark for quantitatively assessing robot navigation methods. As an automated …

BenchmarkingRobot Navigation

Lipschitz Safe Bayesian Optimization for Automotive Control

2025-01-22 · Johanna Menn, Pietro Pelizzari, Michael Fleps-Dezasse, Sebastian Trimpe

Controller tuning is a labor-intensive process that requires human intervention and expert knowledge. Bayesian optimization has been applied successfully in different fields to automate this process. However, when tuning…

Bayesian Optimization

Bayesian Learning-Based Adaptive Control for Safety Critical Systems

2019-10-05 · David D. Fan, Jennifer Nguyen, Rohan Thakker, Nikhilesh Alatur 외

Deep learning has enjoyed much recent success, and applying state-of-the-art model learning methods to controls is an exciting prospect. However, there is a strong reluctance to use these methods on safety-critical syste…

Autonomous VehiclesBayesian InferenceGaussian ProcessesInterpretable Machine Learning

A Measurement of the Kuiper Belt's Mean Plane From Objects Classified By Machine Learning

2023-04-27 · Ian C. Matheson, Renu Malhotra

Mean plane measurements of the Kuiper Belt from observational data are of interest for their potential to test dynamical models of the solar system. Recent measurements have yielded inconsistent results. Here we report a…