Multi-Armed Bandits

Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles AISTATS 2023 Flexible Budgets in Restless Bandits: A Primal-Dual Algorithm for Efficient Budget Allocation AAAI 2023 Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits AISTATS 2023 High-dimensional Contextual Bandit Problem without Sparsity NeurIPS 2023 Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback ICML 2023 Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms NeurIPS 2023 Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data NeurIPS 2023 Incentivizing Exploration with Linear Contexts and Combinatorial Actions ICML 2023 Increasing Impact of Mobile Health Programs: SAHELI for Maternal and Child Care AAAI 2023 Information-Directed Selection for Top-Two Algorithms COLT 2023 Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory COLT 2023 Interactive Learning with Pricing for Optimal and Stable Allocations in Markets AISTATS 2023 Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning ICML 2023 Last Switch Dependent Bandits with Monotone Payoff Functions ICML 2023 Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection ICLR 2023 Learning and Collusion in Multi-unit Auctions NeurIPS 2023 Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees ICML 2023 Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment ICLR 2023 Learning Revenue Maximization Using Posted Prices for Stochastic Strategic Patient Buyers AAAI 2023 Learning to Rank under Multinomial Logit Choice JMLR 2023 Leveraging Demonstrations to Improve Online Learning: Quality Matters ICML 2023 Local Justice and Machine Learning: Modeling and Inferring Dynamic Ethical Preferences toward Allocations AAAI 2023 Logarithmic regret in communicating MDPs: Leveraging known dynamics with bandits ACML 2023 Meta-Learning Adversarial Bandit Algorithms NeurIPS 2023 Meta-Learning for Simple Regret Minimization AAAI 2023