{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"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":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2006.10800","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-06-18","cited_by_count":197},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"2007.06700","title":"Revisiting Fundamentals of Experience Replay","created":"2020-07-13","cited_by_count":175},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"id":"1803.03835","title":"Kickstarting Deep Reinforcement Learning","created":"2018-03-10","cited_by_count":81},{"id":"2006.05826","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","created":"2020-06-10","cited_by_count":75},{"id":"1611.06694","title":"Training Sparse Neural Networks","created":"2016-11-21","cited_by_count":73},{"id":"1906.02768","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","created":"2019-06-06","cited_by_count":73},{"id":"1906.10732","title":"The Difficulty of Training Sparse Neural Networks","created":"2019-06-25","cited_by_count":62},{"id":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49},{"id":"1910.01465","title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","created":"2019-10-03","cited_by_count":47},{"id":"2001.05012","title":"PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning","created":"2020-01-14","cited_by_count":30},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30},{"id":"2105.01648","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","created":"2021-05-04","cited_by_count":24},{"id":"1910.12708","title":"Evaluating Lottery Tickets Under Distributional Shifts","created":"2019-10-28","cited_by_count":23},{"id":"2005.03454","title":"Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture","created":"2020-05-04","cited_by_count":23},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","cited_by_count":19},{"id":"1904.00346","title":"Fully Learnable Group Convolution for Acceleration of Deep Neural Networks","created":"2019-03-31","cited_by_count":16},{"id":"2303.00912","title":"Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning","created":"2023-03-02","cited_by_count":14},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8},{"id":"2003.01040","title":"Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph","created":"2020-03-02","cited_by_count":7},{"id":"2012.09456","title":"Stabilizing Q Learning Via Soft Mellowmax Operator","created":"2020-12-17","cited_by_count":6},{"id":"2210.16624","title":"LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning","created":"2022-10-29","cited_by_count":1}],"next_cursor":null}