{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:22:20Z","timestamp":1742966540219,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031303326"},{"type":"electronic","value":"9783031303333"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-30333-3_32","type":"book-chapter","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T06:02:45Z","timestamp":1682661765000},"page":"242-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic IP Core Generator for\u00a0FPGA-Based Q-Learning Hardware Accelerators"],"prefix":"10.1007","author":[{"given":"Lorenzo","family":"Canese","sequence":"first","affiliation":[]},{"given":"Gian Carlo","family":"Cardarilli","sequence":"additional","affiliation":[]},{"given":"Luca","family":"Di Nunzio","sequence":"additional","affiliation":[]},{"given":"Rocco","family":"Fazzolari","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Re","sequence":"additional","affiliation":[]},{"given":"Sergio","family":"Span\u00f3","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,29]]},"reference":[{"key":"32_CR1","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"key":"32_CR2","doi-asserted-by":"publisher","first-page":"13753","DOI":"10.1109\/ACCESS.2022.3146518","volume":"10","author":"M Rothmann","year":"2022","unstructured":"Rothmann, M., Porrmann, M.: A survey of domain-specific architectures for reinforcement learning. IEEE Access 10, 13753\u201313767 (2022)","journal-title":"IEEE Access"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Waseem, S.M., Roy, S.K.: Hardware realization of reinforcement learning algorithms for edge devices. In: VLSI and Hardware Implementations Using Modern Machine Learning Methods, pp. 233\u2013254. CRC Press (2021)","DOI":"10.1201\/9781003201038-12"},{"key":"32_CR4","unstructured":"Su, J.D., Tsai, P.Y.: Processing element architecture design for deep reinforcement learning with flexible block floating point exploiting signal statistics. In: 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 82\u201387. IEEE (2020)"},{"issue":"3","key":"32_CR5","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"32_CR6","doi-asserted-by":"publisher","first-page":"107749","DOI":"10.1016\/j.compeleceng.2022.107749","volume":"99","author":"GC Cardarilli","year":"2022","unstructured":"Cardarilli, G.C., et al.: An FPGA-based multi-agent reinforcement learning timing synchronizer. Comput. Electr. Eng. 99, 107749 (2022)","journal-title":"Comput. Electr. Eng."},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Liu, X., Diao, J., Li, N.: A FPGA-based accelerator implementation for path planning using q_learning algorithm. J. Phys. Conf. Ser. 2245, 012014 (2022). IOP Publishing","DOI":"10.1088\/1742-6596\/2245\/1\/012014"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Cardarilli, G.C., et al.: \u201cMR Q-Learning\u201d algorithm for efficient hardware implementations. In: 2021 55th Asilomar Conference on Signals, Systems, and Computers, pp. 1186\u20131190. IEEE (2021)","DOI":"10.1109\/IEEECONF53345.2021.9723147"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Sahoo, S.S., Baranwal, A.R., Ullah, S., Kumar, A.: MemOReL: a memory-oriented optimization approach to reinforcement learning on FPGA-based embedded systems. In: Proceedings of the 2021 on Great Lakes Symposium on VLSI, pp. 339\u2013346 (2021)","DOI":"10.1145\/3453688.3461533"},{"issue":"9","key":"32_CR10","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1109\/TCAD.2020.3028350","volume":"40","author":"AR Baranwal","year":"2020","unstructured":"Baranwal, A.R., Ullah, S., Sahoo, S.S., Kumar, A.: ReLAccS: a multilevel approach to accelerator design for reinforcement learning on FPGA-based systems. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 40(9), 1754\u20131767 (2020)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Meng, Y., Kuppannagari, S., Rajat, R., Srivastava, A., Kannan, R., Prasanna, V.: QTAccel: a generic FPGA based design for Q-table based reinforcement learning accelerators. In: 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 107\u2013114. IEEE (2020)","DOI":"10.1109\/IPDPSW50202.2020.00024"},{"key":"32_CR12","doi-asserted-by":"publisher","first-page":"186340","DOI":"10.1109\/ACCESS.2019.2961174","volume":"7","author":"S Span\u00f3","year":"2019","unstructured":"Span\u00f3, S., et al.: An efficient hardware implementation of reinforcement learning: the Q-learning algorithm. IEEE Access 7, 186340\u2013186351 (2019)","journal-title":"IEEE Access"},{"key":"32_CR13","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/ACCESS.2018.2885950","volume":"7","author":"LM Da Silva","year":"2018","unstructured":"Da Silva, L.M., Torquato, M.F., Fernandes, M.A.: Parallel implementation of reinforcement learning Q-learning technique for FPGA. IEEE Access 7, 2782\u20132798 (2018)","journal-title":"IEEE Access"},{"issue":"12","key":"32_CR14","doi-asserted-by":"publisher","first-page":"9889","DOI":"10.1109\/JIOT.2022.3163364","volume":"9","author":"J Sun","year":"2022","unstructured":"Sun, J., Sharma, N., Chakareski, J., Mastronarde, N., Lao, Y.: Hardware acceleration for post-decision state reinforcement learning in IoT systems. IEEE Internet Things J. 9(12), 9889\u20139903 (2022)","journal-title":"IEEE Internet Things J."},{"key":"32_CR15","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/978-3-030-66729-0_32","volume-title":"Applications in Electronics Pervading Industry, Environment and Society","author":"GC Cardarilli","year":"2021","unstructured":"Cardarilli, G.C., et al.: An action-selection policy generator for reinforcement learning hardware accelerators. In: Saponara, S., De Gloria, A. (eds.) ApplePies 2020. LNEE, vol. 738, pp. 267\u2013272. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-66729-0_32"}],"container-title":["Lecture Notes in Electrical Engineering","Applications in Electronics Pervading Industry, Environment and Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30333-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T10:35:57Z","timestamp":1729334157000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30333-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031303326","9783031303333"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30333-3_32","relation":{},"ISSN":["1876-1100","1876-1119"],"issn-type":[{"type":"print","value":"1876-1100"},{"type":"electronic","value":"1876-1119"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ApplePies","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications in Electronics Pervading Industry, Environment and Society","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Genoa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"applepies2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/applepies.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}