{"list":"other","total":143,"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":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1710.10571","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","created":"2017-10-29","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":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1804.09699","title":"Towards Fast Computation of Certified Robustness for ReLU Networks","created":"2018-04-25","cited_by_count":255},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1705.08475","title":"Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation","created":"2017-05-23","cited_by_count":185},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2010.15920","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","created":"2020-10-29","cited_by_count":175},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","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":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"1910.13393","title":"Constrained Reinforcement Learning Has Zero Duality Gap","created":"2019-10-29","cited_by_count":151},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"1412.5068","title":"Towards Deep Neural Network Architectures Robust to Adversarial Examples","created":"2014-12-11","cited_by_count":146},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"2006.16908","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","created":"2020-06-30","cited_by_count":142},{"id":"1702.02453","title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","created":"2017-02-08","cited_by_count":141},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"1803.08287","title":"Learning-based Model Predictive Control for Safe Exploration","created":"2018-03-22","cited_by_count":120},{"id":"1910.07224","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","created":"2019-10-16","cited_by_count":119},{"id":"2010.14603","title":"Learning to be Safe: Deep RL with a Safety Critic","created":"2020-10-27","cited_by_count":116},{"id":"1910.01075","title":"Learning Neural Causal Models from Unknown Interventions","created":"2019-10-02","cited_by_count":113},{"id":"1711.09883","title":"AI Safety Gridworlds","created":"2017-11-27","cited_by_count":110},{"id":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","cited_by_count":105},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"id":"1404.3862","title":"Optimizing the CVaR via Sampling","created":"2014-04-15","cited_by_count":99},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"1611.03071","title":"Fairness in Reinforcement Learning","created":"2016-11-09","cited_by_count":95},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"1701.04143","title":"Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks","created":"2017-01-16","cited_by_count":91},{"id":"1808.00924","title":"The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems","created":"2018-08-02","cited_by_count":88},{"id":"2003.12613","title":"Adaptive Reward-Poisoning Attacks against Reinforcement Learning","created":"2020-03-27","cited_by_count":86},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"1810.01032","title":"Reinforcement Learning with Perturbed Rewards","created":"2018-10-02","cited_by_count":79},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"1906.07516","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","created":"2019-06-18","cited_by_count":78},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"2006.12136","title":"Safe Reinforcement Learning via Curriculum Induction","created":"2020-06-22","cited_by_count":74},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"1709.07643","title":"OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World","created":"2017-09-22","cited_by_count":70},{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69},{"id":"2206.09682","title":"SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles","created":"2022-06-20","cited_by_count":66},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"2001.09684","title":"Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning","created":"2020-01-27","cited_by_count":61},{"id":"1910.12156","title":"Convergent Policy Optimization for Safe Reinforcement Learning","created":"2019-10-26","cited_by_count":57},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57},{"id":"1810.03779","title":"Reinforcement Learning for Improving Agent Design","created":"2018-10-09","cited_by_count":56},{"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":"1907.13196","title":"Wasserstein Robust Reinforcement Learning","created":"2019-07-30","cited_by_count":54},{"id":"1906.10571","title":"Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals","created":"2019-06-24","cited_by_count":50},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50},{"id":"1909.12906","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","created":"2019-09-16","cited_by_count":49},{"id":"1910.12908","title":"Certified Adversarial Robustness for Deep Reinforcement Learning","created":"2019-10-28","cited_by_count":47},{"id":"2002.11635","title":"Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization","created":"2020-02-19","cited_by_count":47},{"id":"1803.07551","title":"Meta Reinforcement Learning with Latent Variable Gaussian Processes","created":"2018-03-20","cited_by_count":44},{"id":"1803.00404","title":"Deep Defense: Training DNNs with Improved Adversarial Robustness","created":"2018-02-23","cited_by_count":42},{"id":"1902.08708","title":"Distributionally Robust Reinforcement Learning","created":"2019-02-23","cited_by_count":42}],"next_cursor":"100"}