{"list":"other","total":56,"rows":[{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1711.08013","title":"OSQP: An Operator Splitting Solver for Quadratic Programs","created":"2017-11-21","cited_by_count":161},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"2106.01969","title":"Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games","created":"2021-06-03","cited_by_count":93},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67},{"id":"2007.03458","title":"Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications","created":"2020-07-05","cited_by_count":62},{"id":"1710.09988","title":"Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes","created":"2017-10-27","cited_by_count":57},{"id":"2202.04129","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence","created":"2022-02-08","cited_by_count":57},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56},{"id":"1909.12823","title":"A Generalized Training Approach for Multiagent Learning","created":"2019-09-27","cited_by_count":54},{"id":"2006.13912","title":"Unified Reinforcement Q-Learning for Mean Field Game and Control Problems","created":"2020-06-24","cited_by_count":49},{"id":"1907.02633","title":"On the Convergence of Model Free Learning in Mean Field Games","created":"2019-07-04","cited_by_count":48},{"id":"2103.00623","title":"Scaling up Mean Field Games with Online Mirror Descent","created":"2021-02-28","cited_by_count":32},{"id":"1612.07878","title":"Markov-Nash Equilibria in Mean-Field Games with Discounted Cost","created":"2016-12-23","cited_by_count":31},{"id":"2002.05513","title":"Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach","created":"2020-02-13","cited_by_count":30},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30},{"id":"2112.01280","title":"Learning Graphon Mean Field Games and Approximate Nash Equilibria","created":"2021-11-29","cited_by_count":28},{"id":"2002.02513","title":"Multi Type Mean Field Reinforcement Learning","created":"2020-02-06","cited_by_count":26},{"id":"2002.09806","title":"Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games","created":"2020-02-23","cited_by_count":26},{"id":"2212.14449","title":"Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games","created":"2022-12-29","cited_by_count":26},{"id":"2003.06069","title":"A General Framework for Learning Mean-Field Games","created":"2020-03-13","cited_by_count":25},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20},{"id":"1910.07498","title":"Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games","created":"2019-10-16","cited_by_count":19},{"id":"2012.15791","title":"Partially Observable Mean Field Reinforcement Learning","created":"2020-12-31","cited_by_count":16},{"id":"2106.13755","title":"Reinforcement Learning for Mean Field Games, with Applications to Economics","created":"2021-06-25","cited_by_count":15},{"id":"2111.08350","title":"Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO","created":"2021-11-16","cited_by_count":14},{"id":"2209.03880","title":"Learning Sparse Graphon Mean Field Games","created":"2022-09-08","cited_by_count":14},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14},{"id":"2112.09099","title":"Decentralized Mean Field Games","created":"2021-12-16","cited_by_count":12},{"id":"2312.06659","title":"Convergence of Multi-Scale Reinforcement Q-Learning Algorithms for Mean Field Game and Control Problems","created":"2023-12-11","cited_by_count":10},{"id":"1802.07902","title":"On the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplings","created":"2018-02-22","cited_by_count":9},{"id":"2206.09608","title":"MF-OMO: An Optimization Formulation of Mean-Field Games","created":"2022-06-20","cited_by_count":9},{"id":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","cited_by_count":9},{"id":"2402.05757","title":"When is Mean-Field Reinforcement Learning Tractable and Relevant?","created":"2024-02-08","cited_by_count":8},{"id":"2007.00099","title":"Splitting methods for a class of non-potential mean field games","created":"2020-06-30","cited_by_count":6},{"id":"2208.10138","title":"Learning Correlated Equilibria in Mean-Field Games","created":"2022-08-22","cited_by_count":6},{"id":"2304.08630","title":"MFGLib: A Library for Mean-Field Games","created":"2023-04-17","cited_by_count":6},{"id":"2305.12553","title":"Markov $\\alpha$-Potential Games","created":"2023-05-21","cited_by_count":6},{"id":"2305.14329","title":"Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria","created":"2023-05-23","cited_by_count":5},{"id":"2210.04110","title":"Optimization frameworks and sensitivity analysis of Stackelberg mean-field games","created":"2022-10-08","cited_by_count":4},{"id":"1812.06196","title":"Mean-field games of optimal stopping: a relaxed solution approach","created":"2018-12-14","cited_by_count":2},{"id":"2312.12067","title":"Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property","created":"2023-12-19","cited_by_count":2},{"id":"2202.11428","title":"Linear Programming Fictitious Play algorithm for Mean Field Games with optimal stopping and absorption","created":"2022-02-23","cited_by_count":1},{"id":"2403.20290","title":"Monotone inclusion methods for a class of second-order non-potential mean-field games","created":"2024-03-29","cited_by_count":1}],"next_cursor":null}