{"list":"other","total":65,"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"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":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1502.07943","title":"Non-stochastic Best Arm Identification and Hyperparameter Optimization","created":"2015-02-27","cited_by_count":221},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1811.12808","title":"Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning","created":"2018-11-13","cited_by_count":157},{"id":"1603.05629","title":"Discriminative Embeddings of Latent Variable Models for Structured Data","created":"2016-03-17","cited_by_count":131},{"id":"1703.00548","title":"Evolving Deep Neural Networks","created":"2017-03-01","cited_by_count":95},{"id":"1711.06782","title":"Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning","created":"2017-11-18","cited_by_count":90},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"2007.08794","title":"Discovering Reinforcement Learning Algorithms","created":"2020-07-17","cited_by_count":77},{"id":"1809.10124","title":"Learning Navigation Behaviors End-to-End with AutoRL","created":"2018-09-26","cited_by_count":70},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"1901.10500","title":"Discretizing Continuous Action Space for On-Policy Optimization","created":"2019-01-29","cited_by_count":68},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"2002.02518","title":"Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits","created":"2020-02-06","cited_by_count":63},{"id":"1812.06855","title":"Bayesian Optimization in AlphaGo","created":"2018-12-17","cited_by_count":55},{"id":"2007.08433","title":"Meta-Gradient Reinforcement Learning with an Objective Discovered Online","created":"2020-07-16","cited_by_count":52},{"id":"2004.00980","title":"Action Space Shaping in Deep Reinforcement Learning","created":"2020-04-02","cited_by_count":46},{"id":"1906.11527","title":"Hyp-RL : Hyperparameter Optimization by Reinforcement Learning","created":"2019-06-27","cited_by_count":36},{"id":"1901.09330","title":"Reward Shaping via Meta-Learning","created":"2019-01-27","cited_by_count":32},{"id":"2009.01555","title":"Sample-Efficient Automated Deep Reinforcement Learning","created":"2020-09-03","cited_by_count":32},{"id":"1905.07628","title":"Evolving Rewards to Automate Reinforcement Learning","created":"2019-05-18","cited_by_count":31},{"id":"1906.09807","title":"Proximal Distilled Evolutionary Reinforcement Learning","created":"2019-06-24","cited_by_count":27},{"id":"1903.11774","title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","created":"2019-03-28","cited_by_count":25},{"id":"1905.04100","title":"Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization","created":"2019-02-19","cited_by_count":24},{"id":"1806.06161","title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","created":"2018-06-16","cited_by_count":23},{"id":"2010.14680","title":"Learning to Represent Action Values as a Hypergraph on the Action Vertices","created":"2020-10-28","cited_by_count":23},{"id":"1905.09855","title":"Distributional Policy Optimization: An Alternative Approach for Continuous Control","created":"2019-05-23","cited_by_count":22},{"id":"1607.00446","title":"A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning","created":"2016-07-02","cited_by_count":20},{"id":"1902.00843","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","created":"2019-02-03","cited_by_count":18},{"id":"1705.11159","title":"Reinforcement Learning for Learning Rate Control","created":"2017-05-31","cited_by_count":16},{"id":"1508.03391","title":"Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems","created":"2015-08-14","cited_by_count":9},{"id":"2004.12117","title":"A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning","created":"2020-04-25","cited_by_count":5},{"id":"2106.02229","title":"Differentiable Architecture Search for Reinforcement Learning","created":"2021-06-04","cited_by_count":4},{"id":"1805.04748","title":"Towards Autonomous Reinforcement Learning: Automatic Setting of Hyper-parameters using Bayesian Optimization","created":"2018-05-12","cited_by_count":2},{"id":"2003.01751","title":"Automatic Hyper-Parameter Optimization Based on Mapping Discovery from Data to Hyper-Parameters","created":"2020-03-03","cited_by_count":1}],"next_cursor":null}