{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"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":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2201.05624","title":"Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next","created":"2022-01-14","cited_by_count":608},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1711.04574","title":"Learning Explanatory Rules from Noisy Data","created":"2017-11-13","cited_by_count":211},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"1906.03393","title":"Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling","created":"2019-06-08","cited_by_count":119},{"id":"1906.05799","title":"Deep Reinforcement Learning for Cyber Security","created":"2019-06-13","cited_by_count":95},{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80},{"id":"2008.09293","title":"A Composable Specification Language for Reinforcement Learning Tasks","created":"2020-08-21","cited_by_count":69},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62},{"id":"1904.10729","title":"Neural Logic Reinforcement Learning","created":"2019-04-24","cited_by_count":53},{"id":"2306.01439","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction","created":"2023-06-02","cited_by_count":46},{"id":"1909.01387","title":"Making Efficient Use of Demonstrations to Solve Hard Exploration Problems","created":"2019-09-03","cited_by_count":45},{"id":"2006.01110","title":"Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas","created":"2020-06-01","cited_by_count":36},{"id":"2105.08158","title":"The Confluence of Networks, Games and Learning","created":"2021-05-17","cited_by_count":26},{"id":"1704.05539","title":"Beating Atari with Natural Language Guided Reinforcement Learning","created":"2017-04-18","cited_by_count":24},{"id":"1907.02908","title":"On Inductive Biases in Deep Reinforcement Learning","created":"2019-07-05","cited_by_count":24},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23},{"id":"2002.05135","title":"On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning","created":"2020-02-12","cited_by_count":19},{"id":"2007.03328","title":"Guided Exploration with Proximal Policy Optimization using a Single Demonstration","created":"2020-07-07","cited_by_count":19},{"id":"2402.18781","title":"Conjectural Online Learning with First-order Beliefs in Asymmetric Information Stochastic Games","created":"2024-02-29","cited_by_count":14},{"id":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14},{"id":"2402.12499","title":"Automated Security Response through Online Learning with Adaptive Conjectures","created":"2024-02-19","cited_by_count":13},{"id":"1908.08578","title":"On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning","created":"2019-08-22","cited_by_count":12},{"id":"2012.14043","title":"Blackwell Online Learning for Markov Decision Processes","created":"2020-12-28","cited_by_count":12},{"id":"2210.03209","title":"Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation","created":"2022-10-06","cited_by_count":12},{"id":"2006.02579","title":"Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains","created":"2020-06-03","cited_by_count":11},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11},{"id":"2306.06766","title":"Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning","created":"2023-06-11","cited_by_count":11},{"id":"2410.17431","title":"Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks","created":"2024-10-22","cited_by_count":9},{"id":"2110.14789","title":"Millimeter Wave Wireless Assisted Robot Navigation with Link State Classification","created":"2021-10-27","cited_by_count":7},{"id":"2306.13800","title":"A First Order Meta Stackelberg Method for Robust Federated Learning","created":"2023-06-23","cited_by_count":7},{"id":"2208.06448","title":"RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents","created":"2022-08-12","cited_by_count":4},{"id":"2304.01161","title":"Is Stochastic Mirror Descent Vulnerable to Adversarial Delay Attacks? A Traffic Assignment Resilience Study","created":"2023-04-03","cited_by_count":4},{"id":"2310.04579","title":"Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":4},{"id":"2503.00385","title":"Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective","created":"2025-03-01","cited_by_count":3},{"id":"2011.09241","title":"Indoor Point-to-Point Navigation with Deep Reinforcement Learning and Ultra-wideband","created":"2020-11-18","cited_by_count":2},{"id":"2403.15636","title":"On the Variational Interpretation of Mirror Play in Monotone Games","created":"2024-03-22","cited_by_count":2}],"next_cursor":null}