{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:26:14Z","timestamp":1750220774134,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,11,16]],"date-time":"2020-11-16T00:00:00Z","timestamp":1605484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,11,16]]},"DOI":"10.1145\/3380446.3430619","type":"proceedings-article","created":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T22:27:07Z","timestamp":1606256827000},"page":"37-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Cost Optimization at Early Stages of Design Using Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Lorenzo","family":"Servadei","sequence":"first","affiliation":[{"name":"Infineon Technologies AG & Johannes Kepler University Linz, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiapeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9","family":"Arjona-Medina","sequence":"additional","affiliation":[{"name":"Johannes Kepler University of Linz, Linz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Werner","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG & Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volkan","family":"Esen","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sepp","family":"Hochreiter","sequence":"additional","affiliation":[{"name":"Johannes Kepler University of Linz, Linz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"Ecker","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG & Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Wille","sequence":"additional","affiliation":[{"name":"Johannes Kepler University of Linz & Software Competence Center Hagenberg GmbH, Linz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,11,16]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"J Anderson et al","author":"E.","year":"1994","unstructured":"E. J Anderson et al . 1994 . Genetic algorithms for combinatorial optimization: the assemble line balancing problem. ORSA Journal on Computing ( 1994). E. J Anderson et al. 1994. Genetic algorithms for combinatorial optimization: the assemble line balancing problem. ORSA Journal on Computing (1994)."},{"key":"e_1_3_2_2_2_1","volume-title":"Arjona-Medina et al","author":"J.","year":"2019","unstructured":"J. A. Arjona-Medina et al . 2019 . RUDDER : Return decomposition for delayed rewards. In NeurIPS. J. A. Arjona-Medina et al. 2019. RUDDER: Return decomposition for delayed rewards. In NeurIPS."},{"key":"e_1_3_2_2_3_1","unstructured":"Irwan Bello etal 2016. Neural Combinatorial Optimization with Reinforcement Learning. (2016).  Irwan Bello et al. 2016. Neural Combinatorial Optimization with Reinforcement Learning. (2016)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"A. Colorni etal 1996. Heuristics from nature for hard combinatorial optimization problems. International Transactions in Operational Research (1996).  A. Colorni et al. 1996. Heuristics from nature for hard combinatorial optimization problems. International Transactions in Operational Research (1996).","DOI":"10.1111\/j.1475-3995.1996.tb00032.x"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"W. Ecker etal 2017. Metamodeling and code generation in the hardware\/software interface domain. In Handbook of Hard.\/Soft. Codesign.  W. Ecker et al. 2017. Metamodeling and code generation in the hardware\/software interface domain. In Handbook of Hard.\/Soft. Codesign.","DOI":"10.1007\/978-94-017-7267-9_32"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1538756"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1986079.1986220"},{"key":"e_1_3_2_2_9_1","unstructured":"H. Hu etal 2017. Solving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method. (2017).  H. Hu et al. 2017. Solving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method. (2017)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2190621"},{"key":"e_1_3_2_2_11_1","volume-title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization.","author":"Laterre A.","year":"2018","unstructured":"A. Laterre 2018 . Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization. (2018). A. Laterre et al. 2018. Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization. (2018)."},{"key":"e_1_3_2_2_12_1","unstructured":"A. Mirhoseini etal 2020. Chip Placement with Deep Reinforcement Learning. arXiv preprint arXiv:2004.10746 (2020).  A. Mirhoseini et al. 2020. Chip Placement with Deep Reinforcement Learning. arXiv preprint arXiv:2004.10746 (2020)."},{"key":"e_1_3_2_2_13_1","unstructured":"J. Schulman etal 2017. Proximal Policy Optimization Algorithms.  J. Schulman et al. 2017. Proximal Policy Optimization Algorithms."},{"key":"e_1_3_2_2_14_1","volume-title":"Automation Test in Europe Conf. Exh. (DATE).","author":"Servadei L.","year":"2019","unstructured":"L. Servadei 2019 . Accurate Cost Estimation of Memory Systems Inspired by Machine Learning for Computer Vision. In Design , Automation Test in Europe Conf. Exh. (DATE). L. Servadei et al. 2019. Accurate Cost Estimation of Memory Systems Inspired by Machine Learning for Computer Vision. In Design, Automation Test in Europe Conf. Exh. (DATE)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/RECONFIG.2018.8641736"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3312046"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969540"}],"event":{"name":"MLCAD '20: 2020 ACM\/IEEE Workshop on Machine Learning for CAD","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"Virtual Event Iceland","acronym":"MLCAD '20"},"container-title":["Proceedings of the 2020 ACM\/IEEE Workshop on Machine Learning for CAD"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3380446.3430619","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3380446.3430619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:20Z","timestamp":1750200080000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3380446.3430619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,16]]},"references-count":17,"alternative-id":["10.1145\/3380446.3430619","10.1145\/3380446"],"URL":"https:\/\/doi.org\/10.1145\/3380446.3430619","relation":{},"subject":[],"published":{"date-parts":[[2020,11,16]]},"assertion":[{"value":"2020-11-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}