{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"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":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1906.06316","title":"Towards Stable and Efficient Training of Verifiably Robust Neural Networks","created":"2019-06-14","cited_by_count":205},{"id":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1910.07207","title":"Soft Actor-Critic for Discrete Action Settings","created":"2019-10-16","cited_by_count":174},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"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":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116},{"id":"2002.08550","title":"Learning to Walk in the Real World with Minimal Human Effort","created":"2020-02-20","cited_by_count":111},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"1406.3339","title":"Algorithms for CVaR Optimization in MDPs","created":"2014-06-12","cited_by_count":99},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"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":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"2005.07099","title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":63},{"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":"2002.06063","title":"Robust Reinforcement Learning via Adversarial training with Langevin Dynamics","created":"2020-02-14","cited_by_count":45},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43},{"id":"2206.04436","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","created":"2022-06-09","cited_by_count":41},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38},{"id":"1712.09344","title":"Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger","created":"2017-12-23","cited_by_count":35},{"id":"2007.07176","title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","created":"2020-07-14","cited_by_count":30},{"id":"1909.02583","title":"Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents","created":"2019-09-05","cited_by_count":25},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23},{"id":"1801.00056","title":"f-Divergence constrained policy improvement","created":"2017-12-29","cited_by_count":16},{"id":"1907.04214","title":"Entropic Regularization of Markov Decision Processes","created":"2019-07-06","cited_by_count":15},{"id":"2207.10170","title":"Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks","created":"2022-07-20","cited_by_count":12},{"id":"2211.03413","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","created":"2022-11-07","cited_by_count":11},{"id":"2311.01642","title":"Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula","created":"2023-11-03","cited_by_count":10},{"id":"1901.08021","title":"Robust Temporal Difference Learning for Critical Domains","created":"2019-01-23","cited_by_count":7},{"id":"2305.17342","title":"Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL","created":"2023-05-27","cited_by_count":7},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4}],"next_cursor":null}