{"list":"other","total":64,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"1908.00261","title":"On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift","created":"2019-08-01","cited_by_count":177},{"id":"1902.00923","title":"Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning","created":"2019-02-03","cited_by_count":166},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"1803.08287","title":"Learning-based Model Predictive Control for Safe Exploration","created":"2018-03-22","cited_by_count":120},{"id":"2002.00260","title":"Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning","created":"2020-02-01","cited_by_count":96},{"id":"2006.03041","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","created":"2020-06-04","cited_by_count":95},{"id":"1906.07516","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","created":"2019-06-18","cited_by_count":78},{"id":"2006.14389","title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism","created":"2020-06-24","cited_by_count":76},{"id":"1912.08957","title":"Optimization for deep learning: theory and algorithms","created":"2019-12-19","cited_by_count":70},{"id":"1910.08412","title":"On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation","created":"2019-10-18","cited_by_count":54},{"id":"1803.04848","title":"Soft-Robust Actor-Critic Policy-Gradient","created":"2018-03-11","cited_by_count":37},{"id":"1803.08552","title":"Linear model predictive safety certification for learning-based control","created":"2018-03-22","cited_by_count":37},{"id":"1904.10090","title":"Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version","created":"2019-04-22","cited_by_count":36},{"id":"1809.10121","title":"Safely Learning to Control the Constrained Linear Quadratic Regulator","created":"2018-09-26","cited_by_count":33},{"id":"1909.10165","title":"Deep Reinforcement Learning for Smart Home Energy Management","created":"2019-09-23","cited_by_count":30},{"id":"1707.05878","title":"On-line Building Energy Optimization using Deep Reinforcement Learning","created":"2017-07-18","cited_by_count":27},{"id":"1903.03712","title":"Adaptive Power System Emergency Control using Deep Reinforcement Learning","created":"2019-03-09","cited_by_count":27},{"id":"2006.14156","title":"Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings","created":"2020-06-25","cited_by_count":26},{"id":"1702.07800","title":"On the Origin of Deep Learning","created":"2017-02-24","cited_by_count":23},{"id":"1904.09374","title":"Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning","created":"2019-04-19","cited_by_count":20},{"id":"2011.06709","title":"Active Reinforcement Learning: Observing Rewards at a Cost","created":"2020-11-13","cited_by_count":20},{"id":"2007.02991","title":"Consensus Multi-Agent Reinforcement Learning for Volt-VAR Control in Power Distribution Networks","created":"2020-07-06","cited_by_count":18},{"id":"2003.03681","title":"Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems","created":"2020-03-07","cited_by_count":17},{"id":"2006.12841","title":"Online Multi-agent Reinforcement Learning for Decentralized Inverter-based Volt-VAR Control","created":"2020-06-23","cited_by_count":17},{"id":"2005.11142","title":"Two-stage Deep Reinforcement Learning for Inverter-based Volt-VAR Control in Active Distribution Networks","created":"2020-05-20","cited_by_count":12},{"id":"2011.08004","title":"pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Research","created":"2020-11-11","cited_by_count":10},{"id":"1807.10997","title":"Optimal Tap Setting of Voltage Regulation Transformers Using Batch Reinforcement Learning","created":"2018-07-29","cited_by_count":8},{"id":"2005.06161","title":"Online Scheduling of a Residential Microgrid via Monte-Carlo Tree Search and a Learned Model","created":"2020-05-13","cited_by_count":8},{"id":"2006.12749","title":"Batch-Constrained Reinforcement Learning for Dynamic Distribution Network Reconfiguration","created":"2020-06-23","cited_by_count":8},{"id":"2012.11390","title":"Adversarial Training for a Continuous Robustness Control Problem in Power Systems","created":"2020-12-21","cited_by_count":8},{"id":"1810.01758","title":"A Learning-based Power Management for Networked Microgrids Under Incomplete Information","created":"2018-10-01","cited_by_count":6},{"id":"1903.02526","title":"Safety-Guided Deep Reinforcement Learning via Online Gaussian Process Estimation","created":"2019-03-06","cited_by_count":5},{"id":"2003.03627","title":"Online Residential Demand Response via Contextual Multi-Armed Bandits","created":"2020-03-07","cited_by_count":5},{"id":"2006.07476","title":"Combining Model-Based and Model-Free Methods for Nonlinear Control: A Provably Convergent Policy Gradient Approach","created":"2020-06-12","cited_by_count":5},{"id":"1903.01065","title":"Distributed Optimal Voltage Control with Asynchronous and Delayed Communication","created":"2019-03-04","cited_by_count":4},{"id":"1906.10815","title":"Nested Reinforcement Learning Based Control for Protective Relays in Power Distribution Systems","created":"2019-06-26","cited_by_count":4},{"id":"2010.05153","title":"Online Learning and Distributed Control for Residential Demand Response","created":"2020-10-11","cited_by_count":4},{"id":"1410.2931","title":"Optimal load-side control for frequency regulation in smart grids","created":"2014-10-11","cited_by_count":3},{"id":"1810.11121","title":"Optimal Distributed Feedback Voltage Control under Limited Reactive Power","created":"2018-10-25","cited_by_count":2},{"id":"1811.00892","title":"Distributed Automatic Load-Frequency Control with Optimality in Power Systems","created":"2018-11-02","cited_by_count":1}],"next_cursor":null}