{"list":"other","total":59,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"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":"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":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"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":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1707.06690","title":"DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning","created":"2017-07-20","cited_by_count":266},{"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":"2012.05876","title":"Neurosymbolic AI: The 3rd Wave","created":"2020-12-10","cited_by_count":255},{"id":"1711.03902","title":"Neural-Symbolic Learning and Reasoning: A Survey and Interpretation","created":"2017-11-10","cited_by_count":196},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1711.05851","title":"Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning","created":"2017-11-15","cited_by_count":161},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"1906.04477","title":"Causal Discovery with Reinforcement Learning","created":"2019-06-11","cited_by_count":145},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"2003.00330","title":"Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective","created":"2020-02-29","cited_by_count":95},{"id":"1908.06976","title":"A survey on intrinsic motivation in reinforcement learning","created":"2019-08-19","cited_by_count":81},{"id":"1811.00090","title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning","created":"2018-10-31","cited_by_count":78},{"id":"2010.06002","title":"Thinking Fast and Slow in AI","created":"2020-10-12","cited_by_count":70},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66},{"id":"2005.10619","title":"A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments","created":"2020-05-19","cited_by_count":62},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58},{"id":"2009.12612","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","created":"2020-09-26","cited_by_count":49},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45},{"id":"1609.05518","title":"Towards Deep Symbolic Reinforcement Learning","created":"2016-09-18","cited_by_count":42},{"id":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31},{"id":"2110.10963","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","created":"2021-10-21","cited_by_count":30},{"id":"1702.07800","title":"On the Origin of Deep Learning","created":"2017-02-24","cited_by_count":23},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23},{"id":"1804.08597","title":"Towards Symbolic Reinforcement Learning with Common Sense","created":"2018-04-23","cited_by_count":12},{"id":"2104.06890","title":"An Introduction of mini-AlphaStar","created":"2021-04-14","cited_by_count":10},{"id":"2103.08228","title":"Learning Symbolic Rules for Interpretable Deep Reinforcement Learning","created":"2021-03-15","cited_by_count":9},{"id":"2209.12618","title":"Survey on Applications of Neurosymbolic Artificial Intelligence","created":"2022-09-08","cited_by_count":5},{"id":"2202.08444","title":"A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization","created":"2022-02-17","cited_by_count":1}],"next_cursor":null}