English
Related papers

Related papers: In-Context Learning for Pure Exploration in Contin…

200 papers

Active learning strategies respond to the costly labelling task in a supervised classification by selecting the most useful unlabelled examples in training a predictive model. Many conventional active learning algorithms focus on refining…

Machine Learning · Computer Science 2014-08-12 Djallel Bouneffouf

We study batched bandit experiments and consider the problem of inference conditional on the realized stopping time, assignment probabilities, and target parameter, where all of these may be chosen adaptively using information up to the…

Methodology · Statistics 2026-01-21 Jiafeng Chen , Isaiah Andrews

Many engineering problems require identifying feasible domains under implicit constraints. One example is finding acceptable car body styling designs based on constraints like aesthetics and functionality. Current active-learning based…

Machine Learning · Computer Science 2018-01-23 Wei Chen , Mark Fuge

To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks. We focus on the problem of in-context adaptation and exploration, where an agent only relies on…

Machine Learning · Computer Science 2023-05-05 Chentian Jiang , Nan Rosemary Ke , Hado van Hasselt

Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies…

Machine Learning · Computer Science 2019-04-16 Alexander Fabisch

Numerous heuristics and advanced approaches have been proposed for exploration in different settings for deep reinforcement learning. Noise-based exploration generally fares well with dense-shaped rewards and bonus-based exploration with…

Machine Learning · Computer Science 2025-10-22 Sebastian Griesbach , Carlo D'Eramo

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

Computer Vision and Pattern Recognition · Computer Science 2018-09-27 Clemens-Alexander Brust , Christoph Käding , Joachim Denzler

Deep reinforcement learning has enabled human-level or even super-human performance in various types of games. However, the amount of exploration required for learning is often quite large. Deep reinforcement learning also has super-human…

Machine Learning · Computer Science 2021-12-14 Akane Minami , Yu Kono , Tatsuji Takahashi

In multi-armed bandits, the tasks of reward maximization and pure exploration are often at odds with each other. The former focuses on exploiting arms with the highest means, while the latter may require constant exploration across all…

Machine Learning · Computer Science 2024-10-22 Brian Cho , Dominik Meier , Kyra Gan , Nathan Kallus

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to…

Machine Learning · Computer Science 2024-02-07 Liyuan Wang , Xingxing Zhang , Hang Su , Jun Zhu

We study the sample complexity of pure exploration in an online learning problem with a feedback graph. This graph dictates the feedback available to the learner, covering scenarios between full-information, pure bandit feedback, and…

Machine Learning · Statistics 2025-03-12 Alessio Russo , Yichen Song , Aldo Pacchiano

Contextual bandits serve as a fundamental model for many sequential decision making tasks. The most popular theoretically justified approaches are based on the optimism principle. While these algorithms can be practical, they are known to…

Machine Learning · Computer Science 2020-03-17 Botao Hao , Tor Lattimore , Csaba Szepesvari

We study the contextual multi-armed bandit problem with a finite context space (a.k.a. subpopulations), where the learner recommends a best action for each context and is evaluated by context-weighted simple regret. Our guarantees are…

Machine Learning · Computer Science 2026-05-20 Mohammad Shahverdikondori , Jalal Etesami , Negar Kiyavash

We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chosen action is learned. The primary challenge in a variety of…

Machine Learning · Computer Science 2010-06-15 Alex Strehl , John Langford , Sham Kakade , Lihong Li

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Machine Learning · Computer Science 2024-07-02 Alessio Russo , Alexandre Proutiere

In-context learning (ICL) performance depends critically on which demonstrations are placed in the prompt, yet most existing selectors prioritize heuristic notions of relevance or diversity and provide limited insight into the coverage of a…

Machine Learning · Computer Science 2026-04-15 Jiayi Xin , Xiang Li , Evan Qiang , Weiqing He , Tianqi Shang , Weijie J. Su , Qi Long

We study the problem of identifying an anomalous subset of streams under correlated noise, motivated by monitoring and security in cyber-physical systems. This problem can be viewed as a form of combinatorial pure exploration, where each…

Machine Learning · Computer Science 2026-01-27 Zichuan Yang , Yiming Xing

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Machine Learning · Computer Science 2022-12-01 Alain Andres , Esther Villar-Rodriguez , Javier Del Ser

Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…

Machine Learning · Computer Science 2021-05-11 Qi-An Fu , Yinpeng Dong , Hang Su , Jun Zhu

In the reinforcement learning literature, there are many algorithms developed for either Contextual Bandit (CB) or Markov Decision Processes (MDP) environments. However, when deploying reinforcement learning algorithms in the real world,…

Machine Learning · Computer Science 2022-08-02 Kelly W. Zhang , Omer Gottesman , Finale Doshi-Velez