{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:18:36Z","timestamp":1768339116349,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11133176","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Centralized Training and Decentralized Control through the Actor-Critic Paradigm for Highly Optimized Multicores"],"prefix":"10.1109","author":[{"given":"Benedikt","family":"Dietrich","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Chair for Embedded Systems,Karlsuhe,Germany"}]},{"given":"Heba","family":"Khdr","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Chair for Embedded Systems,Karlsuhe,Germany"}]},{"given":"Jorg","family":"Henkel","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Chair for Embedded Systems,Karlsuhe,Germany"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3092270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605612"},{"key":"ref4","article-title":"Releta: Reinforcement learning for thermal-aware task allocation on multicore","volume":"abs\/1912.00189","author":"Yang","year":"2019","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3095028"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10299-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771801"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2011.5941085"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2772822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546574"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid59990.2024.00039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3468161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3176219"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3351791"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3465933"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037717"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3132170"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3004735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2629486"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2006.73"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"33nd International Conference on Machine Learning, ICML, ser. JMLR Workshop and Conference Proceedings","volume":"48","author":"Mnih"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations, ICLR","author":"Lillicrap"},{"key":"ref26","article-title":"What matters in on-policy reinforcement learning? A large-scale empirical study","volume":"abs\/2006.05990","author":"Andrychowicz","year":"2020","journal-title":"CoRR"},{"key":"ref27","article-title":"Intel text core text TM i9-12900kf processor","year":"2021"},{"key":"ref28","first-page":"8024","article-title":"Pytorch: An imperative style, highperformance deep learning library","volume-title":"32th Annual Conference on Neural Information Processing Systems","author":"Paszke"},{"key":"ref29","first-page":"72","article-title":"The PARSEC benchmark suite: characterization and architectural implications","volume-title":"17th International Conference on Parallel Architectures and Compilation Techniques, PACT","author":"Bienia"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1995.524546"},{"key":"ref31","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"35th International Conference on Machine Learning, ICML, ser. Proceedings of Machine Learning Research","volume":"80","author":"Fujimoto"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11133176.pdf?arnumber=11133176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:25:09Z","timestamp":1758000309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11133176","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}