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.
Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers
An Adversarial Analysis of Thompson Sampling for Full-information Online Learning: from Finite to Infinite Action Spaces
Uncertainty-Aware Search and Value Models: Mitigating Search Scaling Flaws in LLMs
When and why randomised exploration works (in linear bandits)
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
Contextual Thompson Sampling via Generation of Missing Data
An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces
Active RLHF via Best Policy Learning from Trajectory Preference Feedback
FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning
Truthful mechanisms for linear bandit games with private contexts
Stochastically Constrained Best Arm Identification with Thompson Sampling
WAPTS: A Weighted Allocation Probability Adjusted Thompson Sampling Algorithm for High-Dimensional and Sparse Experiment Settings
On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise
Generalized Bayesian deep reinforcement learning
An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits
BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings
Fast, Precise Thompson Sampling for Bayesian Optimization
Epinet for Content Cold Start
Sample-Efficient Alignment for LLMs
Minimum Empirical Divergence for Sub-Gaussian Linear Bandits
Planning and Learning in Risk-Aware Restless Multi-Arm Bandit Problem
Optimizing Posterior Samples for Bayesian Optimization via Rootfinding
BanditCAT and AutoIRT: Machine Learning Approaches to Computerized Adaptive Testing and Item Calibration
Bayesian Collaborative Bandits with Thompson Sampling for Improved Outreach in Maternal Health Program
Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks
Distributed Thompson sampling under constrained communication
Aligning AI Agents via Information-Directed Sampling
Queueing Matching Bandits with Preference Feedback
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
Gaussian Process Thompson Sampling via Rootfinding
Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks
Batched Bayesian optimization by maximizing the probability of including the optimum
Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.