{"list":"other","total":53,"rows":[{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"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":264},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1912.09789","title":"A Survey on Distributed Machine Learning","created":"2019-12-20","cited_by_count":188},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124},{"id":"2006.13165","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","created":"2020-06-23","cited_by_count":102},{"id":"1910.10597","title":"Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles","created":"2019-10-23","cited_by_count":100},{"id":"2010.11425","title":"Differentially-Private Federated Linear Bandits","created":"2020-10-22","cited_by_count":83},{"id":"1507.04296","title":"Massively Parallel Methods for Deep Reinforcement Learning","created":"2015-07-15","cited_by_count":82},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81},{"id":"2011.11566","title":"Logarithmic Regret for Reinforcement Learning with Linear Function Approximation","created":"2020-11-23","cited_by_count":79},{"id":"1901.06455","title":"Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems","created":"2019-01-19","cited_by_count":78},{"id":"2011.12692","title":"Towards Playing Full MOBA Games with Deep Reinforcement Learning","created":"2020-11-25","cited_by_count":78},{"id":"2204.02634","title":"Federated Reinforcement Learning with Environment Heterogeneity","created":"2022-04-06","cited_by_count":63},{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56},{"id":"2110.14074","title":"Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee","created":"2021-10-26","cited_by_count":54},{"id":"2007.01891","title":"A Unifying View of Optimism in Episodic Reinforcement Learning","created":"2020-07-03","cited_by_count":52},{"id":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52},{"id":"2007.01980","title":"Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Design","created":"2020-07-04","cited_by_count":51},{"id":"2111.03289","title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","created":"2021-11-05","cited_by_count":44},{"id":"2212.06069","title":"VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation","created":"2022-12-12","cited_by_count":44},{"id":"1806.00877","title":"Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization","created":"2018-06-03","cited_by_count":40},{"id":"1901.08277","title":"Federated Deep Reinforcement Learning","created":"2019-01-24","cited_by_count":35},{"id":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34},{"id":"1705.04862","title":"Efficient Parallel Methods for Deep Reinforcement Learning","created":"2017-05-13","cited_by_count":32},{"id":"2110.01463","title":"Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits","created":"2021-10-04","cited_by_count":31},{"id":"2009.10601","title":"When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network","created":"2020-09-22","cited_by_count":30},{"id":"2206.11489","title":"Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation","created":"2022-06-23","cited_by_count":30},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27},{"id":"2206.10185","title":"Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning","created":"2022-06-21","cited_by_count":27},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23},{"id":"2110.12727","title":"Learning Stochastic Shortest Path with Linear Function Approximation","created":"2021-10-25","cited_by_count":23},{"id":"2203.03684","title":"Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets","created":"2022-03-07","cited_by_count":16},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","cited_by_count":13},{"id":"2112.13181","title":"DeepMTL Pro: Deep Learning Based MultipleTransmitter Localization and Power Estimation","created":"2021-12-25","cited_by_count":10},{"id":"2210.03022","title":"Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning","created":"2022-10-04","cited_by_count":10},{"id":"2003.09540","title":"Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation","created":"2020-03-21","cited_by_count":7},{"id":"2303.04833","title":"Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models with Reinforcement Learning","created":"2023-02-24","cited_by_count":4}],"next_cursor":null}