{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:25:15Z","timestamp":1759332315900,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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":[[2021,11,1]]},"DOI":"10.1109\/iccad51958.2021.9643589","type":"proceedings-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T23:06:46Z","timestamp":1640300806000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["Optimizing VLSI Implementation with Reinforcement Learning - ICCAD Special Session Paper"],"prefix":"10.1109","author":[{"given":"Haoxing","family":"Ren","sequence":"first","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Saad","family":"Godil","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Brucek","family":"Khailany","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Robert","family":"Kirby","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Haiguang","family":"Liao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Siddhartha","family":"Nath","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Jonathan","family":"Raiman","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Rajarshi","family":"Roy","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3380446.3430629"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-9591-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586138"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415690"},{"journal-title":"What is Design Space Optimization?","year":"0","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00152-7"},{"key":"ref16","first-page":"996","article-title":"Finite-sample convergence rates for q-learning and indirect algorithms","author":"kearns","year":"0","journal-title":"Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems II Cambridge MA USA MIT Press"},{"key":"ref17","first-page":"1180","article-title":"Off-policy policy gradient with stationary distribution correction","author":"liu","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref18","article-title":"Off-policy actor-critic","author":"degris","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref19","first-page":"4565","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref6","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"0","journal-title":"AAAI'16 Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586094"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1115\/1.4045044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2007.364463"},{"journal-title":"Introduction to Reinforcement Learning","year":"2017","author":"sutton","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2020-22219"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586188"}],"event":{"name":"2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","start":{"date-parts":[[2021,11,1]]},"location":"Munich, Germany","end":{"date-parts":[[2021,11,4]]}},"container-title":["2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9643423\/9643432\/09643589.pdf?arnumber=9643589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:30:42Z","timestamp":1654547442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9643589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iccad51958.2021.9643589","relation":{},"subject":[],"published":{"date-parts":[[2021,11,1]]}}}