{"list":"other","total":54,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"2007.06558","title":"Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization","created":"2020-07-13","cited_by_count":176},{"id":"1710.11278","title":"Approximating Continuous Functions by ReLU Nets of Minimal Width","created":"2017-10-31","cited_by_count":122},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110},{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101},{"id":"2011.00583","title":"Game-Theoretic Multiagent Reinforcement Learning","created":"2020-11-01","cited_by_count":94},{"id":"1905.08494","title":"Deep Signature Transforms","created":"2019-05-21","cited_by_count":75},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73},{"id":"2205.11393","title":"Generic bounds on the approximation error for physics-informed (and) operator learning","created":"2022-05-23","cited_by_count":65},{"id":"2203.09346","title":"Error estimates for physics informed neural networks approximating the Navier-Stokes equations","created":"2022-03-17","cited_by_count":63},{"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":"1611.07422","title":"Deep Learning Approximation for Stochastic Control Problems","created":"2016-11-02","cited_by_count":55},{"id":"2006.13912","title":"Unified Reinforcement Q-Learning for Mean Field Game and Control Problems","created":"2020-06-24","cited_by_count":49},{"id":"2003.12151","title":"Q-Learning in Regularized Mean-field Games","created":"2020-03-24","cited_by_count":42},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38},{"id":"2002.10113","title":"Alternating the Population and Control Neural Networks to Solve High-Dimensional Stochastic Mean-Field Games","created":"2020-02-24","cited_by_count":35},{"id":"1908.01613","title":"Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II -- The Finite Horizon Case","created":"2019-08-05","cited_by_count":34},{"id":"1910.04295","title":"Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods","created":"2019-10-09","cited_by_count":28},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28},{"id":"2109.09717","title":"Generalization in Mean Field Games by Learning Master Policies","created":"2021-09-20","cited_by_count":28},{"id":"2101.08068","title":"Neural networks-based algorithms for stochastic control and PDEs in finance","created":"2021-01-20","cited_by_count":26},{"id":"2105.13099","title":"On the Universality of Graph Neural Networks on Large Random Graphs","created":"2021-05-27","cited_by_count":26},{"id":"1912.07883","title":"Mean-field Markov decision processes with common noise and open-loop controls","created":"2019-12-17","cited_by_count":25},{"id":"1911.07314","title":"Dynamic Programming Principles for Mean-Field Controls with Learning","created":"2019-11-17","cited_by_count":23},{"id":"2107.04568","title":"Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance","created":"2021-07-09","cited_by_count":20},{"id":"1912.01809","title":"Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games","created":"2019-12-04","cited_by_count":16},{"id":"1904.10554","title":"Deep Q-Learning for Nash Equilibria: Nash-DQN","created":"2019-04-23","cited_by_count":14},{"id":"2106.03272","title":"Signatured Deep Fictitious Play for Mean Field Games with Common Noise","created":"2021-06-06","cited_by_count":12},{"id":"2112.14377","title":"DeepHAM: A Global Solution Method for Heterogeneous Agent Models with Aggregate Shocks","created":"2021-12-29","cited_by_count":11},{"id":"2006.09611","title":"Learning a functional control for high-frequency finance","created":"2020-06-17","cited_by_count":10},{"id":"2008.05519","title":"Convergence of Deep Fictitious Play for Stochastic Differential Games","created":"2020-08-12","cited_by_count":10},{"id":"2108.06740","title":"A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems","created":"2021-08-15","cited_by_count":10},{"id":"2210.04118","title":"Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems","created":"2022-10-08","cited_by_count":9},{"id":"2002.04112","title":"Connecting GANs, MFGs, and OT","created":"2020-02-10","cited_by_count":8},{"id":"1907.05980","title":"Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: I -- The Ergodic Case","created":"2019-07-13","cited_by_count":6},{"id":"2012.06745","title":"Optimal Policies for a Pandemic: A Stochastic Game Approach and a Deep Learning Algorithm","created":"2020-12-12","cited_by_count":6},{"id":"2211.11691","title":"Deep Signature Algorithm for Multi-dimensional Path-Dependent Options","created":"2022-11-21","cited_by_count":6},{"id":"2011.10890","title":"Large-Scale Multi-Agent Deep FBSDEs","created":"2020-11-21","cited_by_count":5},{"id":"2202.07960","title":"Temporal Difference Learning with Continuous Time and State in the Stochastic Setting","created":"2022-02-16","cited_by_count":5},{"id":"1411.3009","title":"A Probabilistic approach to classical solutions of the master equation for large population equilibria","created":"2014-11-11","cited_by_count":4},{"id":"2007.07731","title":"A posteriori error estimates for fully coupled McKean-Vlasov forward-backward SDEs","created":"2020-07-15","cited_by_count":4},{"id":"2008.11757","title":"Deep Learning for Constrained Utility Maximisation","created":"2020-08-26","cited_by_count":4},{"id":"2203.06753","title":"A Machine Learning Enhanced Algorithm for the Optimal Landing Problem","created":"2022-03-13","cited_by_count":4},{"id":"2107.00839","title":"Exploration noise for learning linear-quadratic mean field games","created":"2021-07-02","cited_by_count":3},{"id":"2204.03968","title":"Machine Learning architectures for price formation models","created":"2022-04-08","cited_by_count":2},{"id":"2211.09633","title":"Finite Approximations for Mean Field Type Multi-Agent Control and Their Near Optimality","created":"2022-11-17","cited_by_count":2},{"id":"1901.09585","title":"Learning Mean-Field Games","created":"2019-01-28","cited_by_count":1},{"id":"2003.03968","title":"Mean Field Games of Controls: Finite Difference Approximations","created":"2020-03-09","cited_by_count":1}],"next_cursor":null}