{"total":34,"rows":[{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41,"area":null},{"id":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2207.10786","title":"Delayed Feedback in Generalised Linear Bandits Revisited","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2206.11254","title":"Langevin Monte Carlo for Contextual Bandits","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2103.13929","title":"Multinomial Logit Contextual Bandits: Provable Optimality and Practicality","created":"2021-03-25","cited_by_count":21,"area":null},{"id":"2110.10018","title":"Dynamic pricing and assortment under a contextual MNL demand","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2202.10678","title":"Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning","created":"2022-02-22","cited_by_count":18,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2209.06983","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2103.05750","title":"Regret Bounds for Generalized Linear Bandits under Parameter Drift","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2103.11489","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","created":"2021-03-21","cited_by_count":12,"area":null},{"id":"2203.01198","title":"Linear Stochastic Bandits over a Bit-Constrained Channel","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2206.07883","title":"Combinatorial Pure Exploration of Causal Bandits","created":"2022-06-16","cited_by_count":9,"area":null},{"id":"2105.03962","title":"Stochastic Multi-Armed Bandits with Control Variates","created":"2021-05-09","cited_by_count":7,"area":null},{"id":"2202.02407","title":"An Experimental Design Approach for Regret Minimization in Logistic Bandits","created":"2022-02-04","cited_by_count":7,"area":null},{"id":"2211.09100","title":"Global Optimization with Parametric Function Approximation","created":"2022-11-16","cited_by_count":7,"area":null},{"id":"2301.13392","title":"Combinatorial Causal Bandits without Graph Skeleton","created":"2023-01-31","cited_by_count":7,"area":null},{"id":"2112.06517","title":"Top $K$ Ranking for Multi-Armed Bandit with Noisy Evaluations","created":"2021-12-13","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2106.06616","title":"Learning Competitive Equilibria in Exchange Economies with Bandit Feedback","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2201.04480","title":"Learning to Identify Top Elo Ratings: A Dueling Bandits Approach","created":"2022-01-12","cited_by_count":2,"area":null},{"id":"2104.05613","title":"An Efficient Algorithm for Deep Stochastic Contextual Bandits","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2109.06077","title":"Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2206.08111","title":"On Private Online Convex Optimization: Optimal Algorithms in $\\ell_p$-Geometry and High Dimensional Contextual Bandits","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2205.04528","title":"Selectively Contextual Bandits","created":"2022-05-09","cited_by_count":0,"area":null},{"id":"2206.04180","title":"Learning in Distributed Contextual Linear Bandits Without Sharing the Context","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2212.11603","title":"Sequential Decision Problems with Weak Feedback","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2305.19161","title":"Cooperative Thresholded Lasso for Sparse Linear Bandit","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2410.22488","title":"Privacy-Preserving Dynamic Assortment Selection","created":"2024-10-29","cited_by_count":0,"area":null}],"next_cursor":null}