{"list":"other","total":93,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"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":"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":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"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":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"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":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"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":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"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":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"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":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"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":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1802.07228","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","created":"2018-02-20","cited_by_count":165},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"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":"1708.05144","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","created":"2017-08-17","cited_by_count":121},{"id":"1906.05243","title":"When to use parametric models in reinforcement learning?","created":"2019-06-12","cited_by_count":118},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"1809.05214","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","created":"2018-09-14","cited_by_count":101},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"1911.02140","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","created":"2019-11-05","cited_by_count":88},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"1901.10902","title":"InfoBot: Transfer and Exploration via the Information Bottleneck","created":"2019-01-30","cited_by_count":78},{"id":"1909.11639","title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","created":"2019-09-25","cited_by_count":72},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"2007.14535","title":"Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction","created":"2020-07-29","cited_by_count":66},{"id":"1809.07731","title":"Benchmarking Reinforcement Learning Algorithms on Real-World Robots","created":"2018-09-20","cited_by_count":65},{"id":"2007.12509","title":"Monte-Carlo Tree Search as Regularized Policy Optimization","created":"2020-07-24","cited_by_count":61},{"id":"1812.07544","title":"Information-Directed Exploration for Deep Reinforcement Learning","created":"2018-12-18","cited_by_count":52},{"id":"2005.04305","title":"Measuring the Algorithmic Efficiency of Neural Networks","created":"2020-05-08","cited_by_count":52},{"id":"2007.08433","title":"Meta-Gradient Reinforcement Learning with an Objective Discovered Online","created":"2020-07-16","cited_by_count":52},{"id":"1905.06893","title":"Leveraging exploration in off-policy algorithms via normalizing flows","created":"2019-05-16","cited_by_count":46},{"id":"1904.12691","title":"DAC: The Double Actor-Critic Architecture for Learning Options","created":"2019-04-29","cited_by_count":43},{"id":"1909.11583","title":"Off-Policy Actor-Critic with Shared Experience Replay","created":"2019-09-25","cited_by_count":39},{"id":"1812.02256","title":"Relative Entropy Regularized Policy Iteration","created":"2018-12-05","cited_by_count":32},{"id":"1707.01891","title":"Trust-PCL: An Off-Policy Trust Region Method for Continuous Control","created":"2017-07-06","cited_by_count":30},{"id":"1801.03326","title":"Expected Policy Gradients for Reinforcement Learning","created":"2018-01-10","cited_by_count":28},{"id":"1612.04340","title":"End-to-End Deep Reinforcement Learning for Lane Keeping Assist","created":"2016-12-13","cited_by_count":27},{"id":"1512.01563","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","created":"2015-12-04","cited_by_count":23},{"id":"1909.03198","title":"Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning","created":"2019-09-07","cited_by_count":20},{"id":"1910.07478","title":"Adaptive Trade-Offs in Off-Policy Learning","created":"2019-10-16","cited_by_count":20},{"id":"1802.07564","title":"Clipped Action Policy Gradient","created":"2018-02-21","cited_by_count":19},{"id":"1905.07447","title":"REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning","created":"2019-05-17","cited_by_count":17},{"id":"2002.02873","title":"Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning","created":"2020-02-07","cited_by_count":15},{"id":"1910.05527","title":"Regularizing Model-Based Planning with Energy-Based Models","created":"2019-10-12","cited_by_count":11},{"id":"1809.04720","title":"Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics","created":"2018-09-13","cited_by_count":8},{"id":"1704.04651","title":"The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning","created":"2017-04-15","cited_by_count":7},{"id":"2008.02215","title":"A Time Leap Challenge for SAT Solving","created":"2020-08-05","cited_by_count":6},{"id":"1905.11041","title":"Policy Search by Target Distribution Learning for Continuous Control","created":"2019-05-27","cited_by_count":3},{"id":"2001.05068","title":"Social and Governance Implications of Improved Data Efficiency","created":"2020-01-14","cited_by_count":3},{"id":"2007.13690","title":"Maximum Mutation Reinforcement Learning for Scalable Control","created":"2020-07-24","cited_by_count":2}],"next_cursor":null}