{"list":"other","total":54,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":4885},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"1708.05144","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","created":"2017-08-17","cited_by_count":121},{"id":"1911.02140","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","created":"2019-11-05","cited_by_count":88},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"1804.04154","title":"Reinforcement Learning for UAV Attitude Control","created":"2018-04-11","cited_by_count":48},{"id":"1910.01465","title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","created":"2019-10-03","cited_by_count":47},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"1904.12691","title":"DAC: The Double Actor-Critic Architecture for Learning Options","created":"2019-04-29","cited_by_count":43},{"id":"1705.04862","title":"Efficient Parallel Methods for Deep Reinforcement Learning","created":"2017-05-13","cited_by_count":32},{"id":"1811.03307","title":"Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledge","created":"2018-11-08","cited_by_count":26},{"id":"2009.05429","title":"Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments","created":"2020-09-11","cited_by_count":21},{"id":"1910.05547","title":"Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learning","created":"2019-10-12","cited_by_count":19},{"id":"1811.02696","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","created":"2018-11-06","cited_by_count":12},{"id":"1901.10832","title":"Deep Reinforcement Learning for UAV Navigation Through Massive MIMO Technique","created":"2019-01-30","cited_by_count":10},{"id":"2003.04816","title":"Data Freshness and Energy-Efficient UAV Navigation Optimization: A Deep Reinforcement Learning Approach","created":"2020-02-21","cited_by_count":9},{"id":"2003.10923","title":"Autonomous UAV Navigation: A DDPG-based Deep Reinforcement Learning Approach","created":"2020-03-21","cited_by_count":8},{"id":"1806.00196","title":"Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method","created":"2018-06-01","cited_by_count":7},{"id":"1807.08241","title":"NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images","created":"2018-07-22","cited_by_count":5},{"id":"2007.07793","title":"Developmental Reinforcement Learning of Control Policy of a Quadcopter UAV with Thrust Vectoring Rotors","created":"2020-07-15","cited_by_count":3},{"id":"1811.04584","title":"Navigating Assistance System for Quadcopter with Deep Reinforcement Learning","created":"2018-11-12","cited_by_count":2},{"id":"2001.04560","title":"Dynamic Radar Network of UAVs: A Joint Navigation and Tracking Approach","created":"2020-01-13","cited_by_count":2},{"id":"2002.08415","title":"UAV Aided Search and Rescue Operation Using Reinforcement Learning","created":"2020-02-19","cited_by_count":2},{"id":"2005.05057","title":"Reinforcement Learning for UAV Autonomous Navigation, Mapping and Target Detection","created":"2020-05-05","cited_by_count":2},{"id":"2108.13181","title":"Networks of UAVs of Low-Complexity for Time-Critical Localization","created":"2021-08-07","cited_by_count":2},{"id":"2108.13448","title":"Machine Learning Methods for Management UAV Flocks -- a Survey","created":"2021-08-30","cited_by_count":2}],"next_cursor":null}