{"list":"other","total":73,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1802.05666","title":"Adversarial Risk and the Dangers of Evaluating Against Weak Attacks","created":"2018-02-15","cited_by_count":221},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"2002.05646","title":"Adversarial Machine Learning -- Industry Perspectives","created":"2020-02-04","cited_by_count":122},{"id":"1812.09755","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","created":"2018-12-23","cited_by_count":121},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"id":"1701.04143","title":"Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks","created":"2017-01-16","cited_by_count":91},{"id":"1910.05366","title":"Learning Nearly Decomposable Value Functions Via Communication Minimization","created":"2019-10-11","cited_by_count":86},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"1901.09207","title":"Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning","created":"2019-01-26","cited_by_count":68},{"id":"2005.07099","title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":63},{"id":"2001.09684","title":"Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning","created":"2020-01-27","cited_by_count":61},{"id":"2108.09118","title":"CybORG: A Gym for the Development of Autonomous Cyber Agents","created":"2021-08-20","cited_by_count":60},{"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":"2101.06560","title":"Adversarial Attacks On Multi-Agent Communication","created":"2021-01-17","cited_by_count":49},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42},{"id":"2206.04436","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","created":"2022-06-09","cited_by_count":41},{"id":"2003.03722","title":"On the Robustness of Cooperative Multi-Agent Reinforcement Learning","created":"2020-03-08","cited_by_count":39},{"id":"2107.02367","title":"Discrete-Valued Neural Communication","created":"2021-07-06","cited_by_count":39},{"id":"1904.10090","title":"Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version","created":"2019-04-22","cited_by_count":36},{"id":"1712.09344","title":"Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger","created":"2017-12-23","cited_by_count":35},{"id":"2008.02616","title":"The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning","created":"2020-08-06","cited_by_count":28},{"id":"1909.02583","title":"Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents","created":"2019-09-05","cited_by_count":25},{"id":"2004.06496","title":"Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning","created":"2020-04-11","cited_by_count":24},{"id":"1907.13548","title":"Optimal Attacks on Reinforcement Learning Policies","created":"2019-07-31","cited_by_count":21},{"id":"2108.03803","title":"Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning","created":"2021-08-09","cited_by_count":18},{"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":"1905.11832","title":"Snooping Attacks on Deep Reinforcement Learning","created":"2019-05-28","cited_by_count":17},{"id":"1805.12487","title":"Sequential Attacks on Agents for Long-Term Adversarial Goals","created":"2018-05-31","cited_by_count":16},{"id":"2011.07114","title":"Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents","created":"2020-11-13","cited_by_count":15},{"id":"2108.13093","title":"Investigating Vulnerabilities of Deep Neural Policies","created":"2021-08-30","cited_by_count":15},{"id":"2106.15860","title":"Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning","created":"2021-06-30","cited_by_count":13},{"id":"2109.07723","title":"Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns","created":"2021-09-16","cited_by_count":13},{"id":"1905.12282","title":"CopyCAT: Taking Control of Neural Policies with Constant Attacks","created":"2019-05-29","cited_by_count":12},{"id":"2109.12343","title":"Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems","created":"2021-09-25","cited_by_count":12},{"id":"2012.00508","title":"Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication","created":"2020-12-01","cited_by_count":11},{"id":"2106.08746","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","created":"2021-06-16","cited_by_count":9},{"id":"2110.08956","title":"Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training","created":"2021-10-18","cited_by_count":8},{"id":"2110.04983","title":"Understanding the Safety Requirements for Learning-based Power Systems Operations","created":"2021-10-11","cited_by_count":5},{"id":"2006.00817","title":"Adversarial Attacks on Reinforcement Learning based Energy Management Systems of Extended Range Electric Delivery Vehicles","created":"2020-06-01","cited_by_count":3},{"id":"2109.08904","title":"Towards Resilient Artificial Intelligence: Survey and Research Issues","created":"2021-09-18","cited_by_count":2},{"id":"2111.02845","title":"Attacking Deep Reinforcement Learning-Based Traffic Signal Control Systems with Colluding Vehicles","created":"2021-11-04","cited_by_count":2},{"id":"2111.14833","title":"Adversarial Attacks in Cooperative AI","created":"2021-11-29","cited_by_count":1}],"next_cursor":null}