{"list":"other","total":52,"rows":[{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164},{"id":"1712.06924","title":"Safe Policy Improvement with Baseline Bootstrapping","created":"2017-12-19","cited_by_count":144},{"id":"1803.02815","title":"Sever: A Robust Meta-Algorithm for Stochastic Optimization","created":"2018-03-07","cited_by_count":125},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"1807.01473","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","created":"2018-07-04","cited_by_count":101},{"id":"2002.07066","title":"Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium","created":"2020-02-17","cited_by_count":100},{"id":"1804.07933","title":"Is feature selection secure against training data poisoning?","created":"2018-04-21","cited_by_count":93},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84},{"id":"1608.08182","title":"Data Poisoning Attacks on Factorization-Based Collaborative Filtering","created":"2016-08-29","cited_by_count":83},{"id":"1703.00893","title":"Being Robust (in High Dimensions) Can Be Practical","created":"2017-03-02","cited_by_count":83},{"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":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70},{"id":"2005.07099","title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":63},{"id":"2106.02748","title":"Decentralized Q-Learning in Zero-sum Markov Games","created":"2021-06-04","cited_by_count":58},{"id":"2110.14074","title":"Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee","created":"2021-10-26","cited_by_count":54},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53},{"id":"2106.06630","title":"Corruption-Robust Offline Reinforcement Learning","created":"2021-06-11","cited_by_count":51},{"id":"2205.06811","title":"Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions","created":"2022-05-13","cited_by_count":51},{"id":"1906.10571","title":"Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals","created":"2019-06-24","cited_by_count":50},{"id":"2009.12976","title":"Robust regression with covariate filtering: Heavy tails and adversarial contamination","created":"2020-09-27","cited_by_count":50},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44},{"id":"2007.01394","title":"Robust Linear Regression: Optimal Rates in Polynomial Time","created":"2020-06-29","cited_by_count":42},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42},{"id":"2009.00774","title":"Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics","created":"2020-09-02","cited_by_count":38},{"id":"2212.05949","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","created":"2022-12-12","cited_by_count":33},{"id":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28},{"id":"2010.04157","title":"Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination","created":"2020-10-08","cited_by_count":26},{"id":"2011.10824","title":"Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks","created":"2020-11-21","cited_by_count":24},{"id":"2102.05776","title":"Defense Against Reward Poisoning Attacks in Reinforcement Learning","created":"2021-02-10","cited_by_count":21},{"id":"2206.01888","title":"Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning","created":"2022-06-04","cited_by_count":20},{"id":"2302.13851","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","created":"2023-02-27","cited_by_count":14},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13},{"id":"2110.11763","title":"Game Redesign in No-regret Game Playing","created":"2021-10-18","cited_by_count":8}],"next_cursor":null}