{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1603.01121","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","created":"2016-03-03","cited_by_count":158},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1809.02104","title":"Are adversarial examples inevitable?","created":"2018-09-06","cited_by_count":113},{"id":"1810.02274","title":"Episodic Curiosity through Reachability","created":"2018-10-04","cited_by_count":109},{"id":"1707.09183","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","created":"2017-07-28","cited_by_count":94},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"1511.04143","title":"Deep Reinforcement Learning in Parameterized Action Space","created":"2015-11-13","cited_by_count":68},{"id":"1712.03847","title":"On Quadratic Penalties in Elastic Weight Consolidation","created":"2017-12-11","cited_by_count":55},{"id":"1705.05035","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","created":"2017-05-14","cited_by_count":51},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"1811.00525","title":"On the Geometry of Adversarial Examples","created":"2018-11-01","cited_by_count":43},{"id":"2207.12355","title":"Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation","created":"2022-07-25","cited_by_count":37},{"id":"2006.10410","title":"DREAM: Deep Regret minimization with Advantage baselines and Model-free learning","created":"2020-06-18","cited_by_count":36},{"id":"1801.00209","title":"Deep Reinforcement Learning for List-wise Recommendations","created":"2017-12-30","cited_by_count":35},{"id":"1905.05965","title":"Autonomous Penetration Testing using Reinforcement Learning","created":"2019-05-15","cited_by_count":33},{"id":"2307.07107","title":"Graph Positional and Structural Encoder","created":"2023-07-14","cited_by_count":33},{"id":"2103.07583","title":"Network Environment Design for Autonomous Cyberdefense","created":"2021-03-13","cited_by_count":32},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30},{"id":"1905.12767","title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology","created":"2019-05-29","cited_by_count":27},{"id":"2309.07388","title":"On Autonomous Agents in a Cyber Defence Environment","created":"2023-09-14","cited_by_count":26},{"id":"2303.04926","title":"Automated Cyber Defence: A Review","created":"2023-03-08","cited_by_count":21},{"id":"2109.06449","title":"Deep hierarchical reinforcement agents for automated penetration testing","created":"2021-09-14","cited_by_count":19},{"id":"2008.12234","title":"The Advantage Regret-Matching Actor-Critic","created":"2020-08-27","cited_by_count":17},{"id":"2002.10667","title":"CybORG: An Autonomous Cyber Operations Research Gym","created":"2020-02-25","cited_by_count":16},{"id":"1810.09656","title":"Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space","created":"2018-10-23","cited_by_count":15},{"id":"2202.07415","title":"NeuPL: Neural Population Learning","created":"2022-02-15","cited_by_count":14},{"id":"2205.13005","title":"QGNN: Value Function Factorisation with Graph Neural Networks","created":"2022-05-25","cited_by_count":14},{"id":"1512.01124","title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions","created":"2015-12-03","cited_by_count":13},{"id":"1906.00190","title":"Neural Replicator Dynamics","created":"2019-06-01","cited_by_count":13},{"id":"2004.00470","title":"Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication","created":"2020-04-01","cited_by_count":12},{"id":"2310.05939","title":"Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning","created":"2023-08-25","cited_by_count":12},{"id":"2004.11145","title":"F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning","created":"2020-04-17","cited_by_count":10},{"id":"2108.01696","title":"Linking Common Vulnerabilities and Exposures to the MITRE ATT&CK Framework: A Self-Distillation Approach","created":"2021-08-03","cited_by_count":9},{"id":"1603.04119","title":"Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains","created":"2016-03-14","cited_by_count":8},{"id":"1803.10664","title":"Autonomous Intelligent Cyber-defense Agent (AICA) Reference Architecture. Release 2.0","created":"2018-03-28","cited_by_count":8},{"id":"2104.10262","title":"Network Defense is Not a Game","created":"2021-04-20","cited_by_count":6},{"id":"2302.00797","title":"Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning","created":"2023-02-01","cited_by_count":6},{"id":"1801.02774","title":"Adversarial Spheres","created":"2018-01-09","cited_by_count":5},{"id":"2108.13980","title":"Incorporating Deception into CyberBattleSim for Autonomous Defense","created":"2021-08-31","cited_by_count":5},{"id":"2103.16085","title":"A Taxonomy of Cyber Defence Strategies Against False Data Attacks in Smart Grid","created":"2021-03-30","cited_by_count":4},{"id":"2111.12197","title":"Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS","created":"2021-11-23","cited_by_count":3},{"id":"2008.00511","title":"Curriculum Learning with a Progression Function","created":"2020-08-02","cited_by_count":2}],"next_cursor":null}