{"list":"other","total":74,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"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":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"1906.05030","title":"Fast Task Inference with Variational Intrinsic Successor Features","created":"2019-06-12","cited_by_count":133},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"1906.05243","title":"When to use parametric models in reinforcement learning?","created":"2019-06-12","cited_by_count":118},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108},{"id":"1707.05589","title":"On the State of the Art of Evaluation in Neural Language Models","created":"2017-07-18","cited_by_count":104},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"1803.07055","title":"Simple random search provides a competitive approach to reinforcement learning","created":"2018-03-19","cited_by_count":75},{"id":"1707.09861","title":"Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging","created":"2017-07-31","cited_by_count":73},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"2007.14430","title":"Munchausen Reinforcement Learning","created":"2020-07-28","cited_by_count":69},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59},{"id":"2007.12401","title":"Predictive Information Accelerates Learning in RL","created":"2020-07-24","cited_by_count":56},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"1706.08606","title":"Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study","created":"2017-06-26","cited_by_count":46},{"id":"2010.09163","title":"D2RL: Deep Dense Architectures in Reinforcement Learning","created":"2020-10-19","cited_by_count":42},{"id":"2006.16958","title":"Evaluating the Performance of Reinforcement Learning Algorithms","created":"2020-06-30","cited_by_count":36},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36},{"id":"2010.07470","title":"Masked Contrastive Representation Learning for Reinforcement Learning","created":"2020-10-15","cited_by_count":32},{"id":"1904.06979","title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","created":"2019-04-15","cited_by_count":27},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","cited_by_count":23},{"id":"1809.05676","title":"Deterministic Implementations for Reproducibility in Deep Reinforcement Learning","created":"2018-09-15","cited_by_count":19},{"id":"1909.03772","title":"A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots","created":"2019-09-09","cited_by_count":12},{"id":"2102.12887","title":"Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard","created":"2021-02-25","cited_by_count":12},{"id":"1904.06312","title":"Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments","created":"2019-04-12","cited_by_count":11},{"id":"2001.05209","title":"SEERL: Sample Efficient Ensemble Reinforcement Learning","created":"2020-01-15","cited_by_count":11},{"id":"1709.07588","title":"Abandon Statistical Significance","created":"2017-09-22","cited_by_count":5},{"id":"2102.06782","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","created":"2021-02-12","cited_by_count":4},{"id":"1903.00027","title":"Catalyst.RL: A Distributed Framework for Reproducible RL Research","created":"2019-02-28","cited_by_count":3},{"id":"2107.01904","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","created":"2021-07-05","cited_by_count":2}],"next_cursor":null}