paper-with-me

Papers

Contextual Bandits for Unbounded Context Distributions

2024-08-19 · Puning Zhao, Rongfei Fan, Shaowei Wang, Li Shen, Qixin Zhang, Zong Ke, Tianhang Zheng

Nonparametric contextual bandit is an important model of sequential decision making problems. Under $\alpha$-Tsybakov margin condition, existing research has established a regret bound of $\tilde{O}\left(T^{1-\frac{\alpha+1}{d+2}}\right)$ for bounded supports. However, the optimal regret with unbounded contexts has not been analyzed. The challenge of solving contextual bandit problems with unbounded support is to achieve both exploration-exploitation tradeoff and bias-variance tradeoff simultaneously. In this paper, we solve the nonparametric contextual bandit problem with unbounded contexts. We propose two nearest neighbor methods combined with UCB exploration. The first method uses a fixed $k$. Our analysis shows that this method achieves minimax optimal regret under a weak margin condition and relatively light-tailed context distributions. The second method uses adaptive $k$. By a proper data-driven selection of $k$, this method achieves an expected regret of $\tilde{O}\left(T^{1-\frac{(\alpha+1)\beta}{\alpha+(d+2)\beta}}+T^{1-\beta}\right)$, in which $\beta$ is a parameter describing the tail strength. This bound matches the minimax lower bound up to logarithm factors, indicating that the second method is approximately optimal.

📄 PDF Abstract BibTeX arXiv:2408.09655

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingMulti-Armed BanditsSequential Decision Making

Similar Papers 제목 키워드 기반

Episodic Contextual Bandits with Knapsacks under Conversion Models

2025-07-09 · Wang Chi Cheung, Zitian Li arxiv

We study an online setting, where a decision maker (DM) interacts with contextual bandit-with-knapsack (BwK) instances in repeated episodes. These episodes start with different resource amounts, and the contexts' probabi…

Reinforcement Learning

Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits

2026-09-09 · Hao Li, Jie Xu, Zheng Xie arxiv

Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made for stochastic bandits and non-contextual adversarial bandits, meta-l…

A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems

2026-03-17 · Wei Min Loh, Sajib Kumer Sinha, Ankur Agarwal, Pascal Poupart arxiv

Contextual bandits are incredibly useful in many practical problems. We go one step further by devising a more realistic problem that combines: (1) contextual bandits with dense arm features, (2) non-linear reward functi…

Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms

2020-09-20 · Mengfan Xu, Diego Klabjan

We study the challenging exploration incentive problem in both bandit and reinforcement learning, where the rewards are scale-free and potentially unbounded, driven by real-world scenarios and differing from existing wor…

Multi-Armed Banditsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Online Posterior Sampling with a Diffusion Prior

2024-10-04 · Branislav Kveton, Boris Oreshkin, Youngsuk Park, Aniket Deshmukh 외

Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally efficient but it cannot describe complex d…

Multi-Armed Bandits