{"list":"other","total":65,"rows":[{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"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":"1810.12715","title":"On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models","created":"2018-10-30","cited_by_count":328},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"2006.07869","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","created":"2020-06-14","cited_by_count":212},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"1802.05335","title":"Multimodal Generative Models for Scalable Weakly-Supervised Learning","created":"2018-02-14","cited_by_count":200},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"1610.01206","title":"A Survey of Multi-View Representation Learning","created":"2016-10-03","cited_by_count":107},{"id":"2007.12322","title":"Off-Policy Multi-Agent Decomposed Policy Gradients","created":"2020-07-24","cited_by_count":98},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"1611.01891","title":"Joint Multimodal Learning with Deep Generative Models","created":"2016-11-07","cited_by_count":87},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"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":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74},{"id":"1410.7827","title":"Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictions","created":"2014-10-28","cited_by_count":67},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"2108.07422","title":"Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences","created":"2021-08-17","cited_by_count":66},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58},{"id":"1904.00511","title":"Risk Averse Robust Adversarial Reinforcement Learning","created":"2019-03-31","cited_by_count":57},{"id":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56},{"id":"2006.06455","title":"Learning Individually Inferred Communication for Multi-Agent Cooperation","created":"2020-06-11","cited_by_count":55},{"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":"2110.14300","title":"Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks","created":"2021-10-27","cited_by_count":54},{"id":"2101.06560","title":"Adversarial Attacks On Multi-Agent Communication","created":"2021-01-17","cited_by_count":49},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49},{"id":"1909.02682","title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control","created":"2019-09-06","cited_by_count":46},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42},{"id":"2003.03722","title":"On the Robustness of Cooperative Multi-Agent Reinforcement Learning","created":"2020-03-08","cited_by_count":39},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36},{"id":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36},{"id":"1912.05304","title":"Learning Agent Communication under Limited Bandwidth by Message Pruning","created":"2019-12-03","cited_by_count":31},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31},{"id":"2010.14391","title":"Succinct and Robust Multi-Agent Communication With Temporal Message Control","created":"2020-10-27","cited_by_count":29},{"id":"2008.02616","title":"The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning","created":"2020-08-06","cited_by_count":28},{"id":"2006.00587","title":"Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization","created":"2020-05-31","cited_by_count":26},{"id":"2201.05843","title":"Cooperative Multi-Agent Deep Reinforcement Learning for Reliable Surveillance via Autonomous Multi-UAV Control","created":"2022-01-15","cited_by_count":26},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26},{"id":"2004.06496","title":"Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning","created":"2020-04-11","cited_by_count":24},{"id":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","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":"2109.06795","title":"ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation","created":"2021-09-14","cited_by_count":17},{"id":"2206.10057","title":"Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum","created":"2022-06-21","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":"1910.08285","title":"Multi-View Reinforcement Learning","created":"2019-10-18","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":"2202.08393","title":"Robust Reinforcement Learning via Genetic Curriculum","created":"2022-02-17","cited_by_count":10},{"id":"2109.12508","title":"LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates","created":"2021-09-26","cited_by_count":9},{"id":"2205.09362","title":"Sparse Adversarial Attack in Multi-agent Reinforcement Learning","created":"2022-05-19","cited_by_count":8},{"id":"2206.10158","title":"Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems","created":"2022-06-21","cited_by_count":7},{"id":"2012.08255","title":"Robust Multi-Agent Reinforcement Learning with Social Empowerment for Coordination and Communication","created":"2020-12-15","cited_by_count":6},{"id":"2203.11024","title":"Multi-View Dreaming: Multi-View World Model with Contrastive Learning","created":"2022-03-15","cited_by_count":6}],"next_cursor":null}