{"total":54,"rows":[{"id":"2305.03495","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","created":"2023-05-04","cited_by_count":653,"area":null},{"id":"2102.06129","title":"Meta-Thompson Sampling","created":"2021-02-11","cited_by_count":63,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"area":null},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24,"area":null},{"id":"2109.11301","title":"A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification","created":"2021-09-23","cited_by_count":17,"area":null},{"id":"2303.08816","title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2504.07157","title":"GAAPO: Genetic Algorithmic Applied to Prompt Optimization","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","cited_by_count":10,"area":null},{"id":"2502.08208","title":"Exploring Exploration in Bayesian Optimization","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2107.01689","title":"Restless and Uncertain: Robust Policies for Restless Bandits via Deep Multi-Agent Reinforcement Learning","created":"2021-07-04","cited_by_count":7,"area":null},{"id":"2407.12865","title":"GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2209.09185","title":"Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Bandits","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2301.12595","title":"Adversarial Attacks on Adversarial Bandits","created":"2023-01-30","cited_by_count":6,"area":null},{"id":"2306.06779","title":"Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering","created":"2023-06-11","cited_by_count":6,"area":null},{"id":"2105.14188","title":"We Know What You Want: An Advertising Strategy Recommender System for Online Advertising","created":"2021-05-25","cited_by_count":5,"area":null},{"id":"2211.07092","title":"Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2505.07367","title":"Generalization Bounds and Stopping Rules for Learning with Self-Selected Data","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2109.04433","title":"Extreme Bandits using Robust Statistics","created":"2021-09-09","cited_by_count":4,"area":null},{"id":"2110.01810","title":"Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess","created":"2021-10-05","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2404.12356","title":"Improving the interpretability of GNN predictions through conformal-based graph sparsification","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2412.14382","title":"Balans: Multi-Armed Bandits-based Adaptive Large Neighborhood Search for Mixed-Integer Programming Problem","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2411.05979","title":"Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2510.23214","title":"AUPO -- Abstracted Until Proven Otherwise: A Reward Distribution Based Abstraction Algorithm","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2102.04231","title":"Neurogenetic Programming Framework for Explainable Reinforcement Learning","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2103.13860","title":"Active Inference Tree Search in Large POMDPs","created":"2021-03-25","cited_by_count":2,"area":null},{"id":"2111.11090","title":"Optimistic Temporal Difference Learning for 2048","created":"2021-11-22","cited_by_count":2,"area":null},{"id":"2201.00486","title":"Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2304.07665","title":"Dynamic Exploration-Exploitation Trade-Off in Active Learning Regression with Bayesian Hierarchical Modeling","created":"2023-04-16","cited_by_count":2,"area":null},{"id":"2308.02537","title":"ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2103.06964","title":"Learning Policies for Multilingual Training of Neural Machine Translation Systems","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2405.18626","title":"Causal Contextual Bandits with Adaptive Context","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2406.08713","title":"Batch-Instructed Gradient for Prompt Evolution:Systematic Prompt Optimization for Enhanced Text-to-Image Synthesis","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2502.04399","title":"Online Location Planning for AI-Defined Vehicles: Optimizing Joint Tasks of Order Serving and Spatio-Temporal Heterogeneous Model Fine-Tuning","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2506.02386","title":"Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2106.07088","title":"A new soft computing method for integration of expert's knowledge in reinforcement learn-ing problems","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2107.08988","title":"An Analysis of Reinforcement Learning for Malaria Control","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2111.00870","title":"Statistical Consequences of Dueling Bandits","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2201.01182","title":"Modelling Cournot Games as Multi-agent Multi-armed Bandits","created":"2022-01-01","cited_by_count":0,"area":null},{"id":"2205.10642","title":"MetaNet: Automated Dynamic Selection of Scheduling Policies in Cloud Environments","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2209.05692","title":"Sample Complexity of an Adversarial Attack on UCB-based Best-arm Identification Policy","created":"2022-09-13","cited_by_count":0,"area":null},{"id":"2404.19253","title":"Learning to Communicate Functional States with Nonverbal Expressions for Improved Human-Robot Collaboration","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2405.18068","title":"A Survey of Latent Factor Models in Recommender Systems","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2408.06257","title":"Reciprocal Learning","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2505.24692","title":"Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.10804","title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.23497","title":"Dynamic Trust Calibration Using Contextual Bandits","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.10605","title":"Budget Allocation for Unknown Value Functions in a Lipschitz Space","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2602.24231","title":"Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2607.29375","title":"The Greedy Advantage in Finite-Horizon Bandits","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}