{"list":"other","total":56,"rows":[{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1903.08568","title":"Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices","created":"2019-03-20","cited_by_count":227},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1802.09127","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","created":"2018-02-26","cited_by_count":169},{"id":"1911.07676","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","created":"2019-11-18","cited_by_count":127},{"id":"1906.04697","title":"Variance-reduced $Q$-learning is minimax optimal","created":"2019-06-11","cited_by_count":73},{"id":"1802.09756","title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising","created":"2018-02-27","cited_by_count":65},{"id":"2205.12944","title":"Learning in Mean Field Games: A Survey","created":"2022-05-25","cited_by_count":61},{"id":"1910.12802","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning","created":"2019-10-28","cited_by_count":59},{"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":"1901.11454","title":"Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning","created":"2019-01-31","cited_by_count":57},{"id":"2102.01567","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants","created":"2021-02-02","cited_by_count":57},{"id":"1810.10408","title":"Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks","created":"2018-10-24","cited_by_count":56},{"id":"2006.06626","title":"Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward","created":"2020-06-11","cited_by_count":50},{"id":"1311.1731","title":"Stochastic blockmodel approximation of a graphon: Theory and consistent estimation","created":"2013-11-07","cited_by_count":39},{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38},{"id":"1402.1888","title":"A Consistent Histogram Estimator for Exchangeable Graph Models","created":"2014-02-08","cited_by_count":37},{"id":"2006.06879","title":"Active Sampling for Min-Max Fairness","created":"2020-06-11","cited_by_count":33},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33},{"id":"2109.04024","title":"On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)","created":"2021-09-09","cited_by_count":32},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28},{"id":"2112.01280","title":"Learning Graphon Mean Field Games and Approximate Nash Equilibria","created":"2021-11-29","cited_by_count":28},{"id":"2303.15740","title":"Concentration of Contractive Stochastic Approximation: Additive and Multiplicative Noise","created":"2023-03-28","cited_by_count":26},{"id":"1806.01584","title":"Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning","created":"2018-06-05","cited_by_count":24},{"id":"1806.01492","title":"Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model","created":"2018-06-05","cited_by_count":22},{"id":"2209.12681","title":"More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization","created":"2022-09-26","cited_by_count":19},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17},{"id":"2105.08268","title":"Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach","created":"2021-05-18","cited_by_count":14},{"id":"2210.12320","title":"Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations","created":"2022-10-22","cited_by_count":14},{"id":"2008.10216","title":"Graphon Mean Field Games and the GMFG Equations","created":"2020-08-24","cited_by_count":13},{"id":"2209.04808","title":"Graphon Mean-Field Control for Cooperative Multi-Agent Reinforcement Learning","created":"2022-09-11","cited_by_count":11},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9},{"id":"2412.00661","title":"Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning","created":"2024-12-01","cited_by_count":9},{"id":"2403.00222","title":"Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale","created":"2024-03-01","cited_by_count":8},{"id":"2404.13009","title":"Online Policy Optimization in Unknown Nonlinear Systems","created":"2024-04-19","cited_by_count":8},{"id":"2405.12952","title":"Truncated Variance Reduced Value Iteration","created":"2024-05-21","cited_by_count":8},{"id":"2409.15267","title":"Peer-to-Peer Learning Dynamics of Wide Neural Networks","created":"2024-09-23","cited_by_count":8},{"id":"2502.05812","title":"Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6G","created":"2025-02-09","cited_by_count":7},{"id":"2302.04376","title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-08","cited_by_count":6},{"id":"2411.19526","title":"A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation","created":"2024-11-29","cited_by_count":6},{"id":"2310.17531","title":"Learning Regularized Graphon Mean-Field Games with Unknown Graphons","created":"2023-10-26","cited_by_count":4},{"id":"2502.21240","title":"The Structural Complexity of Matrix-Vector Multiplication","created":"2025-02-28","cited_by_count":4},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","cited_by_count":4},{"id":"2209.03887","title":"Mean Field Games on Weighted and Directed Graphs via Colored Digraphons","created":"2022-09-08","cited_by_count":3},{"id":"2410.17221","title":"Scalable spectral representations for multi-agent reinforcement learning in network MDPs","created":"2024-10-22","cited_by_count":3},{"id":"2601.22057","title":"Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models","created":"2026-01-29","cited_by_count":3},{"id":"2011.08797","title":"Linear Separation via Optimism","created":"2020-11-17","cited_by_count":2},{"id":"2501.17079","title":"Learning Mean Field Control on Sparse Graphs","created":"2025-01-28","cited_by_count":2},{"id":"2509.00981","title":"Enhanced Mean Field Game for Interactive Decision-Making with Varied Stylish Multi-Vehicles","created":"2025-08-31","cited_by_count":2}],"next_cursor":null}