{"list":"other","total":53,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"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":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230},{"id":"1502.07943","title":"Non-stochastic Best Arm Identification and Hyperparameter Optimization","created":"2015-02-27","cited_by_count":221},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","created":"2019-01-07","cited_by_count":192},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"id":"2007.08794","title":"Discovering Reinforcement Learning Algorithms","created":"2020-07-17","cited_by_count":77},{"id":"2006.05826","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","created":"2020-06-10","cited_by_count":75},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"2002.02518","title":"Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits","created":"2020-02-06","cited_by_count":63},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59},{"id":"1812.06855","title":"Bayesian Optimization in AlphaGo","created":"2018-12-17","cited_by_count":55},{"id":"2102.07188","title":"Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces","created":"2021-02-14","cited_by_count":53},{"id":"1601.06650","title":"Time-Varying Gaussian Process Bandit Optimization","created":"2016-01-25","cited_by_count":50},{"id":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38},{"id":"2002.02693","title":"Ready Policy One: World Building Through Active Learning","created":"2020-02-07","cited_by_count":33},{"id":"2009.01555","title":"Sample-Efficient Automated Deep Reinforcement Learning","created":"2020-09-03","cited_by_count":32},{"id":"2006.07593","title":"Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search","created":"2020-06-13","cited_by_count":29},{"id":"1806.01780","title":"Mix&Match - Agent Curricula for Reinforcement Learning","created":"2018-06-05","cited_by_count":27},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19},{"id":"1905.03776","title":"The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study","created":"2019-05-09","cited_by_count":16},{"id":"2009.14825","title":"Deep Reinforcement Learning for Efficient Measurement of Quantum Devices","created":"2020-09-30","cited_by_count":15},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15},{"id":"2109.13800","title":"Faster Improvement Rate Population Based Training","created":"2021-09-28","cited_by_count":13},{"id":"2006.07554","title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","created":"2020-06-13","cited_by_count":11},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8},{"id":"2111.04670","title":"Approximate Neural Architecture Search via Operation Distribution Learning","created":"2021-11-08","cited_by_count":6},{"id":"2012.13091","title":"Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search","created":"2020-12-24","cited_by_count":5},{"id":"2010.15750","title":"Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective","created":"2020-10-29","cited_by_count":3},{"id":"1605.07496","title":"Alternating Optimisation and Quadrature for Robust Control","created":"2016-05-24","cited_by_count":1}],"next_cursor":null}