{"list":"other","total":115,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1906.05113","title":"A Survey of Autonomous Driving: Common Practices and Emerging Technologies","created":"2019-06-12","cited_by_count":379},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1710.10571","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","created":"2017-10-29","cited_by_count":337},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"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":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1712.06924","title":"Safe Policy Improvement with Baseline Bootstrapping","created":"2017-12-19","cited_by_count":144},{"id":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"id":"1607.00215","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","created":"2016-07-01","cited_by_count":117},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"2003.06085","title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","created":"2020-03-13","cited_by_count":115},{"id":"1612.01205","title":"Optimal and Adaptive Off-policy Evaluation in Contextual Bandits","created":"2016-12-04","cited_by_count":111},{"id":"1503.04269","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","created":"2015-03-14","cited_by_count":103},{"id":"1605.04812","title":"Off-policy evaluation for slate recommendation","created":"2016-05-16","cited_by_count":103},{"id":"2002.05700","title":"BADGR: An Autonomous Self-Supervised Learning-Based Navigation System","created":"2020-02-13","cited_by_count":102},{"id":"1807.01473","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","created":"2018-07-04","cited_by_count":101},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"1801.07030","title":"Offline A/B testing for Recommender Systems","created":"2018-01-22","cited_by_count":96},{"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":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"id":"1810.06544","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","created":"2018-10-15","cited_by_count":76},{"id":"1909.05850","title":"Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning","created":"2019-09-12","cited_by_count":75},{"id":"1902.10250","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","created":"2019-02-26","cited_by_count":73},{"id":"1711.09602","title":"Deep Reinforcement Learning for Sepsis Treatment","created":"2017-11-27","cited_by_count":71},{"id":"2003.07305","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","created":"2020-03-16","cited_by_count":71},{"id":"2001.11113","title":"GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values","created":"2020-01-29","cited_by_count":70},{"id":"1603.01312","title":"Learning Physical Intuition of Block Towers by Example","created":"2016-03-03","cited_by_count":68},{"id":"1903.01689","title":"Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment","created":"2019-03-05","cited_by_count":61},{"id":"1805.12298","title":"Evaluating Reinforcement Learning Algorithms in Observational Health Settings","created":"2018-05-31","cited_by_count":60},{"id":"1902.01240","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","created":"2019-02-04","cited_by_count":56},{"id":"1607.03842","title":"Safe Policy Improvement by Minimizing Robust Baseline Regret","created":"2016-07-13","cited_by_count":53},{"id":"1702.07121","title":"Consistent On-Line Off-Policy Evaluation","created":"2017-02-23","cited_by_count":51},{"id":"1704.06300","title":"A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units","created":"2017-04-20","cited_by_count":50},{"id":"1905.09751","title":"Learning When-to-Treat Policies","created":"2019-05-23","cited_by_count":49},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"id":"1901.09455","title":"Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift","created":"2019-01-27","cited_by_count":47},{"id":"1706.00387","title":"Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning","created":"2017-06-01","cited_by_count":40},{"id":"1611.01779","title":"Learning to Act by Predicting the Future","created":"2016-11-06","cited_by_count":36},{"id":"1811.09013","title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","created":"2018-11-22","cited_by_count":34},{"id":"1906.03735","title":"Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning","created":"2019-06-09","cited_by_count":28},{"id":"1712.02838","title":"End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient","created":"2017-12-07","cited_by_count":23},{"id":"1805.10755","title":"Dual Policy Iteration","created":"2018-05-28","cited_by_count":22},{"id":"1907.05079","title":"Safe Policy Improvement with Soft Baseline Bootstrapping","created":"2019-07-11","cited_by_count":22},{"id":"1506.02582","title":"On Convergence of Emphatic Temporal-Difference Learning","created":"2015-06-08","cited_by_count":21},{"id":"1707.02515","title":"A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning","created":"2017-07-09","cited_by_count":20},{"id":"2003.00722","title":"Batch Stationary Distribution Estimation","created":"2020-03-02","cited_by_count":19}],"next_cursor":"100"}