{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T23:05:21Z","timestamp":1730243121674,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,5]]},"DOI":"10.1109\/icfpt56656.2022.9974543","type":"proceedings-article","created":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T20:06:11Z","timestamp":1671134771000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Je","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, KAIST"}]},{"given":"JaeUk","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, KAIST"}]},{"given":"Joo-Young","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, KAIST"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586213"},{"key":"ref33","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00926"},{"key":"ref31","article-title":"Gst: Group-sparse training for accelerating deep reinforcement learning","author":"lee","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref30","article-title":"Block-sparse recurrent neural networks","author":"narang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662447"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1145\/3297858.3304058","article-title":"Fa3c: Fpga-accelerated deep reinforcement learning","author":"cho","year":"2019","journal-title":"Proceedings of the fourth international conference on Architectural support for programming languages and operating systems - AS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/VLSICircuits52068.2021.9492504"},{"key":"ref34","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"ref11","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","author":"peng","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Vain: Attentional multi-agent predictive modeling","author":"hoshen","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Learning when to communicate at scale in multi agent cooperative and competitive tasks","author":"singh","year":"1812","journal-title":"ar Xiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT51103.2020.00011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM51124.2021.00026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref18","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Learning both weights and connections for efficient neural networks","author":"han","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"1","article-title":"Accelerating sparse dnn models without hardware-support via tile-wise sparsity","author":"guo","year":"0","journal-title":"SC14 International Conference for High Performance Computing Networking Storage and Analysis SC"},{"key":"ref4","first-page":"1587","article-title":"Addressing function approxi-mation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2014.109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00064"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grand-master level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb9764"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep rein-forcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"Multi-agent co-operation and the emergence of (natural) language","author":"lazaridou","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref20","first-page":"252","article-title":"Full deep neural network training on a pruned weight budget","volume":"1","author":"lis","year":"2019","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218710"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322263"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3098483"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"}],"event":{"name":"2022 International Conference on Field-Programmable Technology (ICFPT)","start":{"date-parts":[[2022,12,5]]},"location":"Hong Kong","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 International Conference on Field-Programmable Technology (ICFPT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9973804\/9974184\/09974543.pdf?arnumber=9974543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:34:10Z","timestamp":1673897650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9974543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icfpt56656.2022.9974543","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}