paper-with-me

홈 › Papers

LLMs-augmented Contextual Bandit

2023-11-03 · Ali Baheri, Cecilia O. Alm

Contextual bandits have emerged as a cornerstone in reinforcement learning, enabling systems to make decisions with partial feedback. However, as contexts grow in complexity, traditional bandit algorithms can face challenges in adequately capturing and utilizing such contexts. In this paper, we propose a novel integration of large language models (LLMs) with the contextual bandit framework. By leveraging LLMs as an encoder, we enrich the representation of the context, providing the bandit with a denser and more informative view. Preliminary results on synthetic datasets demonstrate the potential of this approach, showing notable improvements in cumulative rewards and reductions in regret compared to traditional bandit algorithms. This integration not only showcases the capabilities of LLMs in reinforcement learning but also opens the door to a new era of contextually-aware decision systems.

📄 PDF Abstract BibTeX arXiv:2311.02268

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Banditsreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Jump Starting Bandits with LLM-Generated Prior Knowledge

2024-06-27 · Parand A. Alamdari, Yanshuai Cao, Kevin H. Wilson

We present substantial evidence demonstrating the benefits of integrating Large Language Models (LLMs) with a Contextual Multi-Armed Bandit framework. Contextual bandits have been widely used in recommendation systems to…

Multi-Armed BanditsRecommendation Systems

Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization

2026-01-17 · Linfeng Du, Ye Yuan, Zichen Zhao, Fuyuan Lyu 외 arxiv

Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alternative to fine-tuning by conditioning …

PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits

2018-05-18 · NeurIPS 2018 12 · Bianca Dumitrascu, Karen Feng, Barbara E. Engelhardt

We address the problem of regret minimization in logistic contextual bandits, where a learner decides among sequential actions or arms given their respective contexts to maximize binary rewards. Using a fast inference pr…

Multi-Armed BanditsThompson Sampling

Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions

2026-03-06 · Dominik P. Hofer, Haochen Song, Rania Islambouli, Laura Hawkins 외 arxiv

Behaviour Change Techniques (BCTs) are central to digital health interventions, yet selecting and delivering effective techniques remains challenging. Contextual bandits enable statistically grounded optimisation of BCT …

Multi-Armed Bandits Meet Large Language Models

2025-05-19 · Djallel Bouneffouf, Raphael Feraud

Bandit algorithms and Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, each addressing distinct yet complementary challenges in decision-making and natural language processing. This…

Decision MakingMulti-Armed BanditsPrompt EngineeringResponse Generation+1