{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1707.06203","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","created":"2017-07-19","cited_by_count":140},{"id":"1906.05799","title":"Deep Reinforcement Learning for Cyber Security","created":"2019-06-13","cited_by_count":95},{"id":"2003.12613","title":"Adaptive Reward-Poisoning Attacks against Reinforcement Learning","created":"2020-03-27","cited_by_count":86},{"id":"2003.12909","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","created":"2020-03-28","cited_by_count":81},{"id":"1810.01032","title":"Reinforcement Learning with Perturbed Rewards","created":"2018-10-02","cited_by_count":79},{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70},{"id":"2010.02966","title":"Reinforcement Learning with Random Delays","created":"2020-10-06","cited_by_count":59},{"id":"2106.05087","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","created":"2021-06-09","cited_by_count":55},{"id":"1906.10571","title":"Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals","created":"2019-06-24","cited_by_count":50},{"id":"2009.00774","title":"Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics","created":"2020-09-02","cited_by_count":38},{"id":"2012.14843","title":"Learning Adversarial Markov Decision Processes with Delayed Feedback","created":"2020-12-29","cited_by_count":33},{"id":"2009.07529","title":"DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing","created":"2020-09-16","cited_by_count":25},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23},{"id":"1712.05441","title":"A Game-Theoretic Taxonomy and Survey of Defensive Deception for Cybersecurity and Privacy","created":"2017-12-14","cited_by_count":22},{"id":"1801.06275","title":"IoT Security Techniques Based on Machine Learning","created":"2018-01-19","cited_by_count":22},{"id":"2102.05776","title":"Defense Against Reward Poisoning Attacks in Reinforcement Learning","created":"2021-02-10","cited_by_count":21},{"id":"1805.00200","title":"Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning","created":"2018-05-01","cited_by_count":17},{"id":"1805.00983","title":"Robust Deep Reinforcement Learning for Security and Safety in Autonomous Vehicle Systems","created":"2018-05-02","cited_by_count":17},{"id":"1906.09687","title":"A Dynamic Games Approach to Proactive Defense Strategies against Advanced Persistent Threats in Cyber-Physical Systems","created":"2019-06-24","cited_by_count":17},{"id":"2103.06967","title":"Adversarial attacks in consensus-based multi-agent reinforcement learning","created":"2021-03-11","cited_by_count":17},{"id":"1809.05258","title":"Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach","created":"2018-09-14","cited_by_count":15},{"id":"2007.10457","title":"Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defense","created":"2020-07-20","cited_by_count":15},{"id":"2102.03022","title":"Deceptive Reinforcement Learning for Privacy-Preserving Planning","created":"2021-02-05","cited_by_count":14},{"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":"1801.05915","title":"Security in Mobile Edge Caching with Reinforcement Learning","created":"2018-01-18","cited_by_count":9},{"id":"1906.12182","title":"Adaptive Honeypot Engagement through Reinforcement Learning of Semi-Markov Decision Processes","created":"2019-06-27","cited_by_count":9},{"id":"1806.01368","title":"Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles","created":"2018-06-04","cited_by_count":8},{"id":"2006.07942","title":"Duplicity Games for Deception Design with an Application to Insider Threat Mitigation","created":"2020-06-14","cited_by_count":8},{"id":"1907.06128","title":"Continuous-Time Markov Decision Processes with Controlled Observations","created":"2019-07-13","cited_by_count":7},{"id":"1907.00459","title":"A Dynamic Game Framework for Rational and Persistent Robot Deception With an Application to Deceptive Pursuit-Evasion","created":"2019-06-30","cited_by_count":6},{"id":"2105.07582","title":"RAIDER: Reinforcement-aided Spear Phishing Detector","created":"2021-05-17","cited_by_count":6},{"id":"2102.06587","title":"Disturbing Reinforcement Learning Agents with Corrupted Rewards","created":"2021-02-12","cited_by_count":4},{"id":"2002.03827","title":"Manipulating Reinforcement Learning: Poisoning Attacks on Cost Signals","created":"2020-02-07","cited_by_count":3},{"id":"2011.04635","title":"Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning","created":"2020-11-09","cited_by_count":3},{"id":"2012.02384","title":"Cross-Layer Coordinated Attacks on Cyber-Physical Systems: A LQG Game Framework with Controlled Observations","created":"2020-12-04","cited_by_count":3},{"id":"1603.02564","title":"Resilient Control under Denial-of-Service:Robust Design","created":"2016-03-08","cited_by_count":2},{"id":"1809.02227","title":"Adaptive Strategic Cyber Defense for Advanced Persistent Threats in Critical Infrastructure Networks","created":"2018-09-06","cited_by_count":2},{"id":"1905.02237","title":"A Differential Game Approach to Decentralized Virus-Resistant Weight Adaptation Policy over Complex Networks","created":"2019-05-06","cited_by_count":2},{"id":"1910.07510","title":"Dynamic Games for Secure and Resilient Control System Design","created":"2019-10-16","cited_by_count":2},{"id":"1806.02852","title":"Fundamental Concepts of Cyber Resilience: Introduction and Overview","created":"2018-06-07","cited_by_count":1},{"id":"1809.02231","title":"Distributed and Optimal Resilient Planning of Large-Scale Interdependent Critical Infrastructures","created":"2018-09-06","cited_by_count":1},{"id":"1911.10100","title":"FlipIn: A Game-Theoretic Cyber Insurance Framework for Incentive-Compatible Cyber Risk Management of Internet of Things","created":"2019-11-22","cited_by_count":1},{"id":"2001.00712","title":"Control Challenges for Resilient Control Systems","created":"2020-01-03","cited_by_count":1},{"id":"2102.12059","title":"Convergence of Bayesian Nash Equilibrium in Infinite Bayesian Games under Discretization","created":"2021-02-24","cited_by_count":1}],"next_cursor":null}