SOTAVerified

Thompson Sampling

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 626–650 of 655 papers

TitleStatusHype
Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space—0
Bayesian learning of the optimal action-value function in a Markov decision process—0
Bayesian Mixture Modelling and Inference based Thompson Sampling in Monte-Carlo Tree Search—0
Bayesian Optimization-Based Beam Alignment for MmWave MIMO Communication Systems—0
Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?—0
Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation—0
Bayesian Quantile and Expectile Optimisation—0
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems—0
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems—0
Belief Flows of Robust Online Learning—0
Best Arm Identification in Batched Multi-armed Bandit Problems—0
Active RLHF via Best Policy Learning from Trajectory Preference Feedback—0
Better Optimism By Bayes: Adaptive Planning with Rich Models—0
Blind Exploration and Exploitation of Stochastic Experts—0
Bootstrapped Thompson Sampling and Deep Exploration—0
BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings—0
Calibrated Fairness in Bandits—0
Causal Bandits without prior knowledge using separating sets—0
Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems—0
Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments—0
Chimera: A Hybrid Machine Learning Driven Multi-Objective Design Space Exploration Tool for FPGA High-Level Synthesis—0
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff—0
Bayesian Analysis of Combinatorial Gaussian Process Bandits—0
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing—0
Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms: A Case with Bounded Regret—0
Show:102550
← PrevPage 26 of 27Next →

No leaderboard results yet.