sublinear regret

The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback L4DC 2023 Variance Reduced Online Gradient Descent for Kernelized Pairwise Learning with Limited Memory ACML 2023 A Bayesian Approach for Stochastic Continuum-armed Bandit with Long-term Constraints AISTATS 2022 A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes AAAI 2022 Can Q-learning be Improved with Advice? COLT 2022 Context Uncertainty in Contextual Bandits with Applications to Recommender Systems AAAI 2022 Learning Competitive Equilibria in Exchange Economies with Bandit Feedback AISTATS 2022 Near-Optimal Multi-Agent Learning for Safe Coverage Control NeurIPS 2022 Neural Contextual Bandits without Regret AISTATS 2022 Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret NeurIPS 2022 Online Reinforcement Learning for Mixed Policy Scopes NeurIPS 2022 Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation ICML 2022 Reinforcement Learning Augmented Asymptotically Optimal Index Policy for Finite-Horizon Restless Bandits AAAI 2022 Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks AISTATS 2022 Triple-Q: A Model-Free Algorithm for Constrained Reinforcement Learning with Sublinear Regret and Zero Constraint Violation AISTATS 2022 Weighted Gaussian Process Bandits for Non-stationary Environments AISTATS 2022 Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy ICML 2022 Black-Box Control for Linear Dynamical Systems COLT 2021 Exploiting Opponents Under Utility Constraints in Sequential Games NeurIPS 2021 Fairness of Exposure in Stochastic Bandits ICML 2021 Individual Fairness in Hindsight JMLR 2021 Memory Efficient Online Meta Learning ICML 2021 Online Control of Unknown Time-Varying Dynamical Systems NeurIPS 2021 Online Learning in Unknown Markov Games ICML 2021 On the Theory of Reinforcement Learning with Once-per-Episode Feedback NeurIPS 2021