{"list":"other","total":53,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"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":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168},{"id":"2004.07213","title":"Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims","created":"2020-04-15","cited_by_count":165},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"2306.14874","title":"ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots","created":"2023-06-26","cited_by_count":152},{"id":"2103.14295","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","created":"2021-03-26","cited_by_count":116},{"id":"2011.01387","title":"Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition","created":"2020-11-02","cited_by_count":96},{"id":"2105.08328","title":"Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning","created":"2021-05-18","cited_by_count":92},{"id":"2202.08345","title":"Learning Smooth Neural Functions via Lipschitz Regularization","created":"2022-02-16","cited_by_count":86},{"id":"1811.08027","title":"Neural Lander: Stable Drone Landing Control using Learned Dynamics","created":"2018-11-19","cited_by_count":85},{"id":"1902.01909","title":"Adaptive Stress Testing for Autonomous Vehicles","created":"2019-02-05","cited_by_count":71},{"id":"2012.05810","title":"Multi-expert learning of adaptive legged locomotion","created":"2020-12-10","cited_by_count":67},{"id":"2011.02404","title":"Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion","created":"2020-11-04","cited_by_count":59},{"id":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45},{"id":"2208.08373","title":"Perceptive Locomotion through Nonlinear Model Predictive Control","created":"2022-08-17","cited_by_count":38},{"id":"2203.14912","title":"Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning","created":"2022-03-23","cited_by_count":37},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35},{"id":"1909.05197","title":"MPC-Net: A First Principles Guided Policy Search","created":"2019-09-11","cited_by_count":34},{"id":"1908.01046","title":"Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation","created":"2019-08-02","cited_by_count":33},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30},{"id":"1901.08680","title":"Multi-objective training of Generative Adversarial Networks with multiple discriminators","created":"2019-01-24","cited_by_count":24},{"id":"2103.06484","title":"Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":22},{"id":"2209.07899","title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","created":"2022-09-16","cited_by_count":21},{"id":"2308.09405","title":"Robust Quadrupedal Locomotion via Risk-Averse Policy Learning","created":"2023-08-18","cited_by_count":19},{"id":"2011.08811","title":"Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs","created":"2020-11-17","cited_by_count":16},{"id":"2206.14049","title":"TAMOLS: Terrain-Aware Motion Optimization for Legged Systems","created":"2022-06-28","cited_by_count":14},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14},{"id":"2306.11035","title":"Adversarial Training Should Be Cast as a Non-Zero-Sum Game","created":"2023-06-19","cited_by_count":13},{"id":"2009.13475","title":"Enhancing Continuous Control of Mobile Robots for End-to-End Visual Active Tracking","created":"2020-09-28","cited_by_count":11},{"id":"2310.09442","title":"Learning Agile Locomotion and Adaptive Behaviors via RL-augmented MPC","created":"2023-10-13","cited_by_count":10},{"id":"2008.00603","title":"Learning Agile Locomotion via Adversarial Training","created":"2020-08-03","cited_by_count":6},{"id":"2201.11928","title":"Quadruped Capturability and Push Recovery via a Switched-Systems Characterization of Dynamic Balance","created":"2022-01-28","cited_by_count":6},{"id":"2205.10098","title":"Adversarial joint attacks on legged robots","created":"2022-05-20","cited_by_count":4},{"id":"2208.07681","title":"Generating a Terrain-Robustness Benchmark for Legged Locomotion: A Prototype via Terrain Authoring and Active Learning","created":"2022-08-16","cited_by_count":3},{"id":"2209.09879","title":"On the Adversarial Scenario-based Safety Testing of Robots: the Comparability and Optimal Aggressiveness","created":"2022-09-20","cited_by_count":3},{"id":"2308.14636","title":"Towards Standardized Disturbance Rejection Testing of Legged Robot Locomotion with Linear Impactor: A Preliminary Study, Observations, and Implications","created":"2023-08-28","cited_by_count":2},{"id":"2112.06185","title":"Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward","created":"2021-12-12","cited_by_count":1}],"next_cursor":null}