Papers with Code 아카이브
Multi-Armed Bandits
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 2
Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.
<span style="color:grey; opacity: 0.6">( Image credit: Microsoft Research )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling
Robust Policy Switching for Antifragile Reinforcement Learning for UAV Deconfliction in Adversarial Environments
Context Attribution with Multi-Armed Bandit Optimization
Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards
A General Framework for Off-Policy Learning with Partially-Observed Reward
Adaptive Data Augmentation for Thompson Sampling
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Stochastic Multi-Objective Multi-Armed Bandits: Regret Definition and Algorithm
Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?
Collaborative Min-Max Regret in Grouped Multi-Armed Bandits
Efficient kernelized bandit algorithms via exploration distributions
Meet Me at the Arm: The Cooperative Multi-Armed Bandits Problem with Shareable Arms
Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget
From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance Adaptation
VirnyFlow: A Design Space for Responsible Model Development
Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms
Stable Thompson Sampling: Valid Inference via Variance Inflation
COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents
Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling
Thompson Sampling in Online RLHF with General Function Approximation
A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing
Offline Clustering of Linear Bandits: Unlocking the Power of Clusters in Data-Limited Environments
Test-Time Scaling of Diffusion Models via Noise Trajectory Search
Representative Action Selection for Large Action-Space Meta-Bandits
KL-regularization Itself is Differentially Private in Bandits and RLHF
Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions
Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype
Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine
In-Domain African Languages Translation Using LLMs and Multi-armed Bandits
Steering Generative Models with Experimental Data for Protein Fitness Optimization
Human in the Loop Adaptive Optimization for Improved Time Series Forecasting
Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima
High-dimensional Nonparametric Contextual Bandit Problem
Dynamic Decision-Making under Model Misspecification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.