Papers with Code 아카이브
Thompson Sampling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Thompson sampling, named after William R. Thompson, is a heuristic for choosing actions that addresses the exploration-exploitation dilemma in the multi-armed bandit problem. It consists of choosing the action that maximizes the expected reward with respect to a randomly drawn belief.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
Incentivizing Exploration with Linear Contexts and Combinatorial Actions
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
Combinatorial Neural Bandits
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation
Discounted Thompson Sampling for Non-Stationary Bandit Problems
Sequential Best-Arm Identification with Application to Brain-Computer Interface
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions
Trajectory-oriented optimization of stochastic epidemiological models
An improved regret analysis for UCB-N and TS-N
Neural Exploitation and Exploration of Contextual Bandits
Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards
Efficiently Tackling Million-Dimensional Multiobjective Problems: A Direction Sampling and Fine-Tuning Approach
Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms
GUTS: Generalized Uncertainty-Aware Thompson Sampling for Multi-Agent Active Search
Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning
A General Recipe for the Analysis of Randomized Multi-Armed Bandit Algorithms
Thompson Sampling for Linear Bandit Problems with Normal-Gamma Priors
The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models
When Combinatorial Thompson Sampling meets Approximation Regret
Approximate Thompson Sampling via Epistemic Neural Networks
Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits
A Bandit Approach to Online Pricing for Heterogeneous Edge Resource Allocation
Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration
Leveraging Demonstrations to Improve Online Learning: Quality Matters
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints
Differentially Private Online Bayesian Estimation With Adaptive Truncation
A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles
Thompson Sampling with Diffusion Generative Prior
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.