English
Related papers

Related papers: Rectified Pessimistic-Optimistic Learning for Stoc…

200 papers

The safe linear bandit problem is a version of the classical stochastic linear bandit problem where the learner's actions must satisfy an uncertain constraint at all rounds. Due its applicability to many real-world settings, this problem…

Machine Learning · Computer Science 2024-03-13 Spencer Hutchinson , Berkay Turan , Mahnoosh Alizadeh

We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty. Traditional regret-minimisation bandit strategies like…

Machine Learning · Computer Science 2025-12-11 Simone Cuonzo , Nina Deliu

Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large family of bandit problems where the unknown underlying reward…

Machine Learning · Computer Science 2021-07-12 Baihe Huang , Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei , Runzhe Wang , Jiaqi Yang

Bandit optimization is a difficult problem, especially if the reward model is high-dimensional. When rewards are modeled by neural networks, sublinear regret has only been shown under strong assumptions, usually when the network is…

Machine Learning · Computer Science 2025-01-14 Mikhail Terekhov

We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is $\rho$-replicable if two executions using shared internal randomness but…

Machine Learning · Computer Science 2026-04-23 Rohan Deb , Udaya Ghai , Karan Singh , Arindam Banerjee

In the bandits with knapsacks framework (BwK) the learner has $m$ resource-consumption (packing) constraints. We focus on the generalization of BwK in which the learner has a set of general long-term constraints. The goal of the learner is…

Machine Learning · Computer Science 2024-05-13 Martino Bernasconi , Matteo Castiglioni , Andrea Celli

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

Machine Learning · Computer Science 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

Machine Learning · Computer Science 2024-05-06 Zhongchang Sun , Sihong He , Fei Miao , Shaofeng Zou

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

Machine Learning · Computer Science 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett

We study a variant of the bandit problem where side information in the form of bounds on the mean of each arm is provided. We prove that these translate to tighter estimates of subgaussian factors and develop novel algorithms that exploit…

Machine Learning · Computer Science 2024-10-29 Nihal Sharma , Soumya Basu , Karthikeyan Shanmugam , Sanjay Shakkottai

This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension…

Machine Learning · Computer Science 2015-11-09 Richard Combes , M. Sadegh Talebi , Alexandre Proutiere , Marc Lelarge

This paper discusses a scenario approach to robust optimization of a blackbox function in a bandit setting. We assume that the blackbox function can be modeled as a Gaussian Process (GP) for every realization of the uncertain parameter. We…

Optimization and Control · Mathematics 2018-05-01 Shaunak D. Bopardikar , Vaibhav Srivastava

This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter their reward observation. We study two cases of this model,…

Machine Learning · Computer Science 2024-08-19 Xuchuang Wang , Jinhang Zuo , Xutong Liu , John C. S. Lui , Mohammad Hajiesmaili

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the…

Machine Learning · Computer Science 2026-03-12 Heyang Zhao , Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call "optimistic closure," which is…

Machine Learning · Statistics 2019-12-10 Yining Wang , Ruosong Wang , Simon S. Du , Akshay Krishnamurthy

The stochastic multi-armed bandit problem is a well-known model for studying the exploration-exploitation trade-off. It has significant possible applications in adaptive clinical trials, which allow for dynamic changes in the treatment…

Machine Learning · Computer Science 2019-06-11 Hossein Aboutalebi , Doina Precup , Tibor Schuster

We study a stochastic bandit problem with a general unknown reward function and a general unknown constraint function. Both functions can be non-linear (even non-convex) and are assumed to lie in a reproducing kernel Hilbert space (RKHS)…

Machine Learning · Computer Science 2022-03-30 Xingyu Zhou , Bo Ji

We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm…

Machine Learning · Computer Science 2023-01-05 Anmol Kagrecha , Jayakrishnan Nair , Krishna Jagannathan

Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a…

Machine Learning · Computer Science 2012-03-05 Alekh Agarwal , Miroslav Dudík , Satyen Kale , John Langford , Robert E. Schapire

The Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed to overcome the central obstacle of what is variously called the fundamental "closed-identifiability problem" of adaptive control, the…

Machine Learning · Computer Science 2021-05-18 Akshay Mete , Rahul Singh , Xi Liu , P. R. Kumar