Exploration-Exploitation

Bandits with Knapsacks beyond the Worst Case NeurIPS 2021 Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning NeurIPS 2021 Combinatorial Pure Exploration with Bottleneck Reward Function NeurIPS 2021 CORe: Capitalizing On Rewards in Bandit Exploration UAI 2021 DDSAS: Dynamic and Differentiable Space-Architecture Search ACML 2021 Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification NeurIPS 2021 Differentially Private Multi-Armed Bandits in the Shuffle Model NeurIPS 2021 Double Explore-then-Commit: Asymptotic Optimality and Beyond COLT 2021 Dual-Mandate Patrols: Multi-Armed Bandits for Green Security AAAI 2021 Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization NeurIPS 2021 Learning from eXtreme Bandit Feedback AAAI 2021 Learning to Stop with Surprisingly Few Samples COLT 2021 Meta-Learning Effective Exploration Strategies for Contextual Bandits AAAI 2021 Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs NeurIPS 2021 Navigating to the Best Policy in Markov Decision Processes NeurIPS 2021 Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature NeurIPS 2021 Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits NeurIPS 2021 Reinforcement Learning with Trajectory Feedback AAAI 2021 Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits AAAI 2021 Stochastic Bandits with Graph Feedback in Non-Stationary Environments AAAI 2021 Temporally-Extended ε-Greedy Exploration ICLR 2021 The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle NeurIPS 2021 The Limits of Optimal Pricing in the Dark NeurIPS 2021 Active Learning for Identification of Linear Dynamical Systems COLT 2020 Choice Bandits NeurIPS 2020