{"list":"other","total":51,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"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":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"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":"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":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"1707.00183","title":"Teacher-Student Curriculum Learning","created":"2017-07-01","cited_by_count":210},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"1403.5341","title":"An Information-Theoretic Analysis of Thompson Sampling","created":"2014-03-21","cited_by_count":178},{"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":"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":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"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":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"1404.3862","title":"Optimizing the CVaR via Sampling","created":"2014-04-15","cited_by_count":99},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2006.09641","title":"Automatic Curriculum Learning through Value Disagreement","created":"2020-06-17","cited_by_count":87},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"1810.06284","title":"CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning","created":"2018-10-15","cited_by_count":79},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"2011.02404","title":"Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion","created":"2020-11-04","cited_by_count":59},{"id":"2104.07662","title":"Auto-Tuned Sim-to-Real Transfer","created":"2021-04-15","cited_by_count":49},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"2002.06063","title":"Robust Reinforcement Learning via Adversarial training with Langevin Dynamics","created":"2020-02-14","cited_by_count":45},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"1810.05751","title":"Policy Transfer with Strategy Optimization","created":"2018-10-12","cited_by_count":43},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29},{"id":"1902.08039","title":"Curiosity-Driven Experience Prioritization via Density Estimation","created":"2019-02-20","cited_by_count":27},{"id":"1909.12892","title":"Automated curricula through setter-solver interactions","created":"2019-09-27","cited_by_count":26},{"id":"1806.06161","title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","created":"2018-06-16","cited_by_count":23},{"id":"2109.06409","title":"Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion","created":"2021-09-14","cited_by_count":14}],"next_cursor":null}