{"list":"other","total":53,"rows":[{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1904.07272","title":"Introduction to Multi-Armed Bandits","created":"2019-04-15","cited_by_count":481},{"id":"1803.04623","title":"Thompson Sampling for Combinatorial Semi-Bandits","created":"2018-03-13","cited_by_count":78},{"id":"1602.04741","title":"Delay and Cooperation in Nonstochastic Bandits","created":"2016-02-15","cited_by_count":71},{"id":"1906.05363","title":"Competing Bandits in Matching Markets","created":"2019-06-12","cited_by_count":56},{"id":"1605.08988","title":"On Explore-Then-Commit Strategies","created":"2016-05-29","cited_by_count":47},{"id":"1809.08151","title":"SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits","created":"2018-09-21","cited_by_count":47},{"id":"2012.07348","title":"Bandit Learning in Decentralized Matching Markets","created":"2020-12-14","cited_by_count":46},{"id":"1506.00779","title":"Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays","created":"2015-06-02","cited_by_count":38},{"id":"2108.08843","title":"Learning Equilibria in Matching Markets from Bandit Feedback","created":"2021-08-19","cited_by_count":34},{"id":"1512.06888","title":"On Distributed Cooperative Decision-Making in Multiarmed Bandits","created":"2015-12-21","cited_by_count":33},{"id":"2006.06613","title":"Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits","created":"2020-06-11","cited_by_count":31},{"id":"2103.07501","title":"Beyond $\\log^2(T)$ Regret for Decentralized Bandits in Matching Markets","created":"2021-03-12","cited_by_count":30},{"id":"2002.10121","title":"The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms","created":"2020-02-24","cited_by_count":28},{"id":"1902.01239","title":"A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players","created":"2019-02-04","cited_by_count":25},{"id":"2003.00162","title":"Decentralized Multi-player Multi-armed Bandits with No Collision Information","created":"2020-02-29","cited_by_count":25},{"id":"1404.5421","title":"Concurrent bandits and cognitive radio networks","created":"2014-04-22","cited_by_count":24},{"id":"1612.01859","title":"Combinatorial semi-bandit with known covariance","created":"2016-12-06","cited_by_count":24},{"id":"1901.08082","title":"Cooperative Online Learning: Keeping your Neighbors Updated","created":"2019-01-23","cited_by_count":22},{"id":"1505.00553","title":"On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits","created":"2015-05-04","cited_by_count":20},{"id":"1808.08416","title":"Multiplayer bandits without observing collision information","created":"2018-08-25","cited_by_count":20},{"id":"1907.03346","title":"Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits","created":"2019-07-07","cited_by_count":20},{"id":"2007.03812","title":"Robust Multi-Agent Multi-Armed Bandits","created":"2020-07-07","cited_by_count":20},{"id":"2102.06246","title":"Regret, stability & fairness in matching markets with bandit learners","created":"2021-02-11","cited_by_count":20},{"id":"2110.14622","title":"Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization","created":"2021-10-27","cited_by_count":18},{"id":"1807.00491","title":"Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings","created":"2018-07-02","cited_by_count":17},{"id":"1904.12233","title":"Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without","created":"2019-04-28","cited_by_count":14},{"id":"2002.01197","title":"Selfish Robustness and Equilibria in Multi-Player Bandits","created":"2020-02-04","cited_by_count":13},{"id":"2011.03896","title":"Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions","created":"2020-11-08","cited_by_count":13},{"id":"2101.11292","title":"Distributed Learning over Markovian Fading Channels for Stable Spectrum Access","created":"2021-01-27","cited_by_count":13},{"id":"1810.11162","title":"Game of Thrones: Fully Distributed Learning for Multi-Player Bandits","created":"2018-10-26","cited_by_count":12},{"id":"1908.01135","title":"Multiplayer Bandit Learning, from Competition to Cooperation","created":"2019-08-03","cited_by_count":12},{"id":"1902.08036","title":"Multi-Player Bandits: The Adversarial Case","created":"2019-02-21","cited_by_count":11},{"id":"2002.07596","title":"Coordination without communication: optimal regret in two players multi-armed bandits","created":"2020-02-14","cited_by_count":11},{"id":"2103.13059","title":"Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information","created":"2021-03-24","cited_by_count":11},{"id":"1910.09091","title":"Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access","created":"2019-10-21","cited_by_count":10},{"id":"1807.00867","title":"Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access","created":"2018-07-02","cited_by_count":9},{"id":"1808.04875","title":"Multi-user Communication Networks: A Coordinated Multi-armed Bandit Approach","created":"2018-08-14","cited_by_count":8},{"id":"2003.07009","title":"Stability and Learning in Strategic Queuing Systems","created":"2020-03-16","cited_by_count":8},{"id":"2106.04228","title":"Decentralized Learning in Online Queuing Systems","created":"2021-06-08","cited_by_count":8},{"id":"2006.15166","title":"Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship","created":"2020-06-26","cited_by_count":7},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7},{"id":"2010.01818","title":"An Efficient Algorithm for Cooperative Semi-Bandits","created":"2020-10-05","cited_by_count":6},{"id":"2111.04873","title":"An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit","created":"2021-11-08","cited_by_count":6},{"id":"2011.01090","title":"On No-Sensing Adversarial Multi-player Multi-armed Bandits with Collision Communications","created":"2020-11-02","cited_by_count":5},{"id":"2101.04388","title":"Dynamic Spectrum Access using Stochastic Multi-User Bandits","created":"2021-01-12","cited_by_count":5},{"id":"1803.06810","title":"Learning to Coordinate in a Decentralized Cognitive Radio Network in Presence of Jammers","created":"2018-03-19","cited_by_count":4},{"id":"2011.10205","title":"Virtues of Patience in Strategic Queuing Systems","created":"2020-11-20","cited_by_count":4},{"id":"2102.07254","title":"Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time","created":"2021-02-14","cited_by_count":4},{"id":"2103.15901","title":"Distributed learning in congested environments with partial information","created":"2021-03-29","cited_by_count":4},{"id":"1402.5666","title":"Dynamic Rate and Channel Selection in Cognitive Radio Systems","created":"2014-02-23","cited_by_count":2},{"id":"1812.05165","title":"On Distributed Multi-player Multiarmed Bandit Problems in Abruptly Changing Environment","created":"2018-12-12","cited_by_count":2},{"id":"1906.00614","title":"Decentralized Spectrum Learning for IoT Wireless Networks Collision Mitigation","created":"2019-06-03","cited_by_count":1}],"next_cursor":null}