{"list":"other","total":56,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15370},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6706},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4900},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4894},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3421},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3049},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2937},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1765},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1111},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":710},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":390},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":265},{"id":"1701.01724","title":"DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker","created":"2017-01-06","cited_by_count":233},{"id":"1708.05344","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","created":"2017-08-17","cited_by_count":204},{"id":"1811.11214","title":"Understanding the impact of entropy on policy optimization","created":"2018-11-27","cited_by_count":176},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"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":"2002.07066","title":"Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium","created":"2020-02-17","cited_by_count":100},{"id":"1912.01825","title":"A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems","created":"2019-12-04","cited_by_count":97},{"id":"2106.01969","title":"Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games","created":"2021-06-03","cited_by_count":93},{"id":"2007.07461","title":"Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity","created":"2020-07-15","cited_by_count":92},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73},{"id":"2102.04540","title":"Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games","created":"2021-02-08","cited_by_count":69},{"id":"1712.00579","title":"Online Reinforcement Learning in Stochastic Games","created":"2017-12-02","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":"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":"1908.06277","title":"Deep Meta Functionals for Shape Representation","created":"2019-08-17","cited_by_count":53},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48},{"id":"2009.11997","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","created":"2020-09-25","cited_by_count":44},{"id":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43},{"id":"1908.11071","title":"Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexity","created":"2019-08-29","cited_by_count":42},{"id":"2102.11494","title":"Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games","created":"2021-02-23","cited_by_count":40},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38},{"id":"2110.10614","title":"Independent Natural Policy Gradient Always Converges in Markov Potential Games","created":"2021-10-20","cited_by_count":37},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35},{"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":"2109.09717","title":"Generalization in Mean Field Games by Learning Master Policies","created":"2021-09-20","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":"2002.02513","title":"Multi Type Mean Field Reinforcement Learning","created":"2020-02-06","cited_by_count":26},{"id":"2007.08483","title":"On Power Laws in Deep Ensembles","created":"2020-07-16","cited_by_count":26},{"id":"1906.00423","title":"Feature-Based Q-Learning for Two-Player Stochastic Games","created":"2019-06-02","cited_by_count":25},{"id":"2001.00248","title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies","created":"2020-01-01","cited_by_count":25},{"id":"2111.11743","title":"Independent Learning in Stochastic Games","created":"2021-11-23","cited_by_count":23},{"id":"2003.04444","title":"Mean Field Games and Applications: Numerical Aspects","created":"2020-03-09","cited_by_count":22},{"id":"2106.06231","title":"Numerical Methods for Mean Field Games and Mean Field Type Control","created":"2021-06-11","cited_by_count":22},{"id":"2006.11917","title":"Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning","created":"2020-06-21","cited_by_count":21},{"id":"1803.05028","title":"Decentralised Learning in Systems with Many, Many Strategic Agents","created":"2018-03-13","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":"2209.03880","title":"Learning Sparse Graphon Mean Field Games","created":"2022-09-08","cited_by_count":14},{"id":"2110.11943","title":"Solving N-player dynamic routing games with congestion: a mean field approach","created":"2021-10-22","cited_by_count":7},{"id":"2203.16223","title":"Hypergraphon Mean Field Games","created":"2022-03-30","cited_by_count":3},{"id":"1807.09226","title":"HyperNets and their application to learning spatial transformations","created":"2018-07-12","cited_by_count":2},{"id":"1909.01209","title":"Discrete Mean Field Games: Existence of Equilibria and Convergence","created":"2019-09-03","cited_by_count":2}],"next_cursor":null}