{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T19:39:20Z","timestamp":1770752360193,"version":"3.50.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1704758,1718570,2112665"],"award-info":[{"award-number":["1704758,1718570,2112665"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,17]]},"DOI":"10.1109\/asp-dac52403.2022.9712578","type":"proceedings-article","created":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T22:39:17Z","timestamp":1645483157000},"page":"500-505","source":"Crossref","is-referenced-by-count":15,"title":["Reinforcement Learning for Electronic Design Automation: Case Studies and Perspectives: (Invited Paper)"],"prefix":"10.1109","author":[{"given":"Ahmet F.","family":"Budak","sequence":"first","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Zixuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Keren","family":"Zhu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]},{"given":"Azalia","family":"Mirhoseini","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Anna","family":"Goldie","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"David Z.","family":"Pan","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume":"70","author":"mirhoseini","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref11","article-title":"A Hierarchical Model for Device Placement","author":"mirhoseini","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","author":"addanki","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Transferable graph optimizers for ML compilers","volume":"abs 2010 12438","author":"zhou","year":"2020","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3372780.3378174"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD52597.2021.9531313"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3003843"},{"key":"ref18","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3124762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643589"},{"key":"ref6","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3451179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-016-9307-4"},{"key":"ref2","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2859220"},{"key":"ref1","article-title":"A survey of deep reinforcement learning in video games","author":"shao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3380446.3430622"},{"key":"ref21","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"SIAM Journal on Control and Optimization"},{"key":"ref24","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref23","author":"mishchenko","year":"0","journal-title":"ABC A System for Sequential Synthesis and Verification"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"}],"event":{"name":"2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,1,17]]},"end":{"date-parts":[[2022,1,20]]}},"container-title":["2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9712466\/9712479\/09712578.pdf?arnumber=9712578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T21:08:30Z","timestamp":1655154510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,17]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/asp-dac52403.2022.9712578","relation":{},"subject":[],"published":{"date-parts":[[2022,1,17]]}}}