{"list":"other","total":63,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"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":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"1301.1942","title":"Bayesian Optimization in a Billion Dimensions via Random Embeddings","created":"2013-01-09","cited_by_count":182},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"1503.01673","title":"High Dimensional Bayesian Optimisation and Bandits via Additive Models","created":"2015-03-05","cited_by_count":139},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"1703.07950","title":"Failures of Gradient-Based Deep Learning","created":"2017-03-23","cited_by_count":80},{"id":"1805.10000","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","created":"2018-05-25","cited_by_count":80},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"1906.04358","title":"Weight Agnostic Neural Networks","created":"2019-06-11","cited_by_count":71},{"id":"1812.08305","title":"Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems","created":"2018-12-20","cited_by_count":67},{"id":"1804.02395","title":"Structured Evolution with Compact Architectures for Scalable Policy Optimization","created":"2018-04-06","cited_by_count":48},{"id":"1810.05751","title":"Policy Transfer with Strategy Optimization","created":"2018-10-12","cited_by_count":43},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"1703.01250","title":"Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization","created":"2017-03-03","cited_by_count":34},{"id":"1802.08842","title":"Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari","created":"2018-02-24","cited_by_count":28},{"id":"1901.11503","title":"Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective","created":"2019-01-31","cited_by_count":27},{"id":"1906.09807","title":"Proximal Distilled Evolutionary Reinforcement Learning","created":"2019-06-24","cited_by_count":27},{"id":"1712.06568","title":"ES Is More Than Just a Traditional Finite-Difference Approximator","created":"2017-12-18","cited_by_count":24},{"id":"1605.08165","title":"Highly-Smooth Zero-th Order Online Optimization Vianney Perchet","created":"2016-05-26","cited_by_count":23},{"id":"2001.02907","title":"Population-Guided Parallel Policy Search for Reinforcement Learning","created":"2020-01-09","cited_by_count":21},{"id":"1904.01049","title":"Bayesian Optimization for Policy Search via Online-Offline Experimentation","created":"2019-04-01","cited_by_count":20},{"id":"1708.02973","title":"Learning Policies for Adaptive Tracking with Deep Feature Cascades","created":"2017-08-09","cited_by_count":19},{"id":"1604.01348","title":"Bayesian Optimization with Exponential Convergence","created":"2016-04-05","cited_by_count":18},{"id":"1712.06564","title":"On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent","created":"2017-12-18","cited_by_count":16},{"id":"1410.7326","title":"Neuroevolution in Games: State of the Art and Open Challenges","created":"2014-10-27","cited_by_count":15},{"id":"1712.06563","title":"Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients","created":"2017-12-18","cited_by_count":15},{"id":"1801.00329","title":"ZOOpt: Toolbox for Derivative-Free Optimization","created":"2017-12-31","cited_by_count":12},{"id":"1504.03293","title":"Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction","created":"2015-04-13","cited_by_count":11},{"id":"1702.07490","title":"Online Meta-learning by Parallel Algorithm Competition","created":"2017-02-24","cited_by_count":9},{"id":"1902.01272","title":"A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control","created":"2019-02-04","cited_by_count":9},{"id":"1905.13278","title":"A Stochastic Derivative Free Optimization Method with Momentum","created":"2019-05-30","cited_by_count":9},{"id":"1607.04817","title":"Global Continuous Optimization with Error Bound and Fast Convergence","created":"2016-07-17","cited_by_count":8},{"id":"1806.01224","title":"Challenges in High-dimensional Reinforcement Learning with Evolution Strategies","created":"2018-06-04","cited_by_count":6},{"id":"1907.09300","title":"Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning","created":"2019-07-22","cited_by_count":5},{"id":"1603.03518","title":"High-dimensional Black-box Optimization via Divide and Approximate Conquer","created":"2016-03-11","cited_by_count":4},{"id":"1710.05958","title":"Gradient-free Policy Architecture Search and Adaptation","created":"2017-10-16","cited_by_count":4},{"id":"1808.05832","title":"Importance mixing: Improving sample reuse in evolutionary policy search methods","created":"2018-08-17","cited_by_count":4},{"id":"1804.03761","title":"Derivative free optimization via repeated classification","created":"2018-04-11","cited_by_count":3},{"id":"1401.6333","title":"The Sampling-and-Learning Framework: A Statistical View of Evolutionary Algorithms","created":"2014-01-24","cited_by_count":2}],"next_cursor":null}