{"list":"other","total":72,"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1812.03596","title":"Task-Free Continual Learning","created":"2018-12-10","cited_by_count":221},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1708.06977","title":"Incremental Learning of Object Detectors without Catastrophic Forgetting","created":"2017-08-23","cited_by_count":208},{"id":"1810.01256","title":"Continual Learning of Context-dependent Processing in Neural Networks","created":"2018-09-29","cited_by_count":179},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"1902.08438","title":"Online Meta-Learning","created":"2019-02-22","cited_by_count":137},{"id":"1810.01963","title":"Learning Scheduling Algorithms for Data Processing Clusters","created":"2018-10-03","cited_by_count":134},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"1710.03641","title":"Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments","created":"2017-10-10","cited_by_count":108},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"2102.05406","title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","created":"2021-02-10","cited_by_count":98},{"id":"1802.09081","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","created":"2018-02-25","cited_by_count":89},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"1904.03711","title":"Neo: A Learned Query Optimizer","created":"2019-04-07","cited_by_count":80},{"id":"1803.06773","title":"Composable Deep Reinforcement Learning for Robotic Manipulation","created":"2018-03-19","cited_by_count":72},{"id":"2101.03778","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","created":"2021-01-11","cited_by_count":70},{"id":"1901.10500","title":"Discretizing Continuous Action Space for On-Policy Optimization","created":"2019-01-29","cited_by_count":68},{"id":"1906.05201","title":"Task Agnostic Continual Learning via Meta Learning","created":"2019-06-12","cited_by_count":53},{"id":"1812.02464","title":"Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting","created":"2018-12-06","cited_by_count":46},{"id":"2009.11997","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","created":"2020-09-25","cited_by_count":44},{"id":"2006.10701","title":"Deep Reinforcement Learning amidst Lifelong Non-Stationarity","created":"2020-06-18","cited_by_count":43},{"id":"2003.06350","title":"Interference and Generalization in Temporal Difference Learning","created":"2020-03-13","cited_by_count":42},{"id":"2005.08158","title":"Optimizing for the Future in Non-Stationary MDPs","created":"2020-05-17","cited_by_count":37},{"id":"1802.07239","title":"Continual Reinforcement Learning with Complex Synapses","created":"2018-02-20","cited_by_count":32},{"id":"1807.02264","title":"Variance Reduction for Reinforcement Learning in Input-Driven Environments","created":"2018-07-06","cited_by_count":30},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26},{"id":"1806.01584","title":"Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning","created":"2018-06-05","cited_by_count":24},{"id":"1811.06626","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","created":"2018-11-15","cited_by_count":24},{"id":"2006.11441","title":"Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes","created":"2020-06-19","cited_by_count":23},{"id":"2105.09452","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","created":"2021-05-20","cited_by_count":18},{"id":"2212.12735","title":"An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context","created":"2022-12-24","cited_by_count":15},{"id":"2008.12858","title":"Real-world Video Adaptation with Reinforcement Learning","created":"2020-08-28","cited_by_count":12},{"id":"2202.06557","title":"Reinforcement Learning in Presence of Discrete Markovian Context Evolution","created":"2022-02-14","cited_by_count":9},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9},{"id":"2009.08346","title":"Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation","created":"2020-09-17","cited_by_count":8},{"id":"2105.08834","title":"Meta-Reinforcement Learning by Tracking Task Non-stationarity","created":"2021-05-18","cited_by_count":8},{"id":"2201.05560","title":"Demystifying Reinforcement Learning in Time-Varying Systems","created":"2022-01-14","cited_by_count":2}],"next_cursor":null}