{"list":"other","total":102,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","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":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"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":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"1407.3501","title":"Robots that can adapt like animals","created":"2014-07-13","cited_by_count":204},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"1912.09789","title":"A Survey on Distributed Machine Learning","created":"2019-12-20","cited_by_count":188},{"id":"1807.05358","title":"Beyond Data and Model Parallelism for Deep Neural Networks","created":"2018-07-14","cited_by_count":179},{"id":"1811.02084","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","created":"2018-11-05","cited_by_count":169},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"1702.05800","title":"Revisiting Distributed Synchronous SGD","created":"2017-02-19","cited_by_count":142},{"id":"2006.09503","title":"Memory-Efficient Pipeline-Parallel DNN Training","created":"2020-06-16","cited_by_count":134},{"id":"2110.05113","title":"Learning High-Speed Flight in the Wild","created":"2021-10-11","cited_by_count":128},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"id":"2106.09388","title":"Deep Subdomain Adaptation Network for Image Classification","created":"2021-06-17","cited_by_count":119},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"1712.06560","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","created":"2017-12-18","cited_by_count":107},{"id":"1809.05214","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","created":"2018-09-14","cited_by_count":101},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"2110.14883","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","created":"2021-10-28","cited_by_count":96},{"id":"1906.05799","title":"Deep Reinforcement Learning for Cyber Security","created":"2019-06-13","cited_by_count":95},{"id":"2006.11751","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","created":"2020-06-21","cited_by_count":93},{"id":"1810.05762","title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","created":"2018-10-12","cited_by_count":90},{"id":"1805.07917","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","created":"2018-05-21","cited_by_count":83},{"id":"1507.04296","title":"Massively Parallel Methods for Deep Reinforcement Learning","created":"2015-07-15","cited_by_count":82},{"id":"1803.07055","title":"Simple random search provides a competitive approach to reinforcement learning","created":"2018-03-19","cited_by_count":75},{"id":"1902.10250","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","created":"2019-02-26","cited_by_count":73},{"id":"1712.09381","title":"RLlib: Abstractions for Distributed Reinforcement Learning","created":"2017-12-26","cited_by_count":54},{"id":"1912.03905","title":"ChainerRL: A Deep Reinforcement Learning Library","created":"2019-12-09","cited_by_count":51},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"1811.00260","title":"Horizon: Facebook's Open Source Applied Reinforcement Learning Platform","created":"2018-11-01","cited_by_count":48},{"id":"2005.14038","title":"HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism","created":"2020-05-28","cited_by_count":46},{"id":"1803.02811","title":"Accelerated Methods for Deep Reinforcement Learning","created":"2018-03-07","cited_by_count":40},{"id":"1903.11314","title":"Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools","created":"2019-03-27","cited_by_count":40},{"id":"1909.11583","title":"Off-Policy Actor-Critic with Shared Experience Replay","created":"2019-09-25","cited_by_count":39},{"id":"2006.16712","title":"Model-based Reinforcement Learning: A Survey","created":"2020-06-30","cited_by_count":39},{"id":"1909.01500","title":"rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch","created":"2019-09-03","cited_by_count":38},{"id":"2008.03911","title":"A Survey on Large-scale Machine Learning","created":"2020-08-10","cited_by_count":35},{"id":"1705.04862","title":"Efficient Parallel Methods for Deep Reinforcement Learning","created":"2017-05-13","cited_by_count":32},{"id":"2107.03992","title":"A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware","created":"2021-07-08","cited_by_count":32},{"id":"1811.03619","title":"Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training","created":"2018-11-08","cited_by_count":28},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25},{"id":"1803.03745","title":"Evolutionary Architecture Search For Deep Multitask Networks","created":"2018-03-10","cited_by_count":23},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19},{"id":"1908.11848","title":"Dynamic Stale Synchronous Parallel Distributed Training for Deep Learning","created":"2019-08-16","cited_by_count":12},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10},{"id":"1310.7610","title":"Distributed Reinforcement Learning via Gossip","created":"2013-10-28","cited_by_count":9},{"id":"1902.03142","title":"Novelty Search for Deep Reinforcement Learning Policy Network Weights by Action Sequence Edit Metric Distance","created":"2019-02-08","cited_by_count":9},{"id":"2011.11012","title":"Distributed Deep Reinforcement Learning: An Overview","created":"2020-11-22","cited_by_count":9},{"id":"2012.09849","title":"High-Throughput Synchronous Deep RL","created":"2020-12-17","cited_by_count":9},{"id":"1810.11787","title":"A Hitchhiker's Guide On Distributed Training of Deep Neural Networks","created":"2018-10-28","cited_by_count":7},{"id":"1910.12453","title":"Asynchronous Methods for Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":7},{"id":"1801.02852","title":"Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes","created":"2018-01-09","cited_by_count":6},{"id":"2003.00433","title":"Fully Asynchronous Policy Evaluation in Distributed Reinforcement Learning over Networks","created":"2020-03-01","cited_by_count":6},{"id":"2003.11164","title":"Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods","created":"2020-03-25","cited_by_count":4},{"id":"2102.12194","title":"Combining Off and On-Policy Training in Model-Based Reinforcement Learning","created":"2021-02-24","cited_by_count":4},{"id":"2204.10562","title":"Efficient Pipeline Planning for Expedited Distributed DNN Training","created":"2022-04-22","cited_by_count":4},{"id":"2207.01251","title":"Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments","created":"2022-07-04","cited_by_count":4},{"id":"2210.00882","title":"MSRL: Distributed Reinforcement Learning with Dataflow Fragments","created":"2022-10-03","cited_by_count":4},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4}],"next_cursor":"100"}