{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T03:25:00Z","timestamp":1781925900453,"version":"3.54.5"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T00:00:00Z","timestamp":1710547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T00:00:00Z","timestamp":1710547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Anhui Engineering Research Center on Information Fusion and Control of Intelligent Robot Open Fund","award":["IFCIR2024002"],"award-info":[{"award-number":["IFCIR2024002"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["Grant Nos. U20A20225 and U2013601"],"award-info":[{"award-number":["Grant Nos. U20A20225 and U2013601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100017128","name":"Science Fund for Distinguished Young Scholars of Anhui Province","doi-asserted-by":"publisher","award":["Grant No. 2308085J02"],"award-info":[{"award-number":["Grant No. 2308085J02"]}],"id":[{"id":"10.13039\/100017128","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Science and Technology Innovation 2030 - \u201dNew Generation Artificial Intelligence\u201d Major Project","award":["Grant No. 2022ZD0116305"],"award-info":[{"award-number":["Grant No. 2022ZD0116305"]}]},{"name":"Innovation Leading Talent of Anhui Province TeZhi plan, the Natural Science Foundation of Hefei, China","award":["Grant No. 202321"],"award-info":[{"award-number":["Grant No. 202321"]}]},{"name":"the CAAI-Huawei Mind Spore Open Fund","award":["Grant No. CAAIXSJLJJ-2022-011A"],"award-info":[{"award-number":["Grant No. CAAIXSJLJJ-2022-011A"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s13042-024-02116-4","type":"journal-article","created":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T14:01:35Z","timestamp":1710597695000},"page":"3715-3731","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Knowledge transfer enabled reinforcement learning for efficient and safe autonomous ship collision avoidance"],"prefix":"10.1007","volume":"15","author":[{"given":"Chengbo","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leihao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhuo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxing","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,16]]},"reference":[{"key":"2116_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.109380","volume":"235","author":"X Zhang","year":"2021","unstructured":"Zhang X, Wang C, Jiang L et al (2021) Collision-avoidance navigation systems for maritime autonomous surface ships: a state of the art survey. Ocean Eng 235:109380. https:\/\/doi.org\/10.1016\/j.oceaneng.2021.109380","journal-title":"Ocean Eng"},{"key":"2116_CR2","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1017\/S0373463323000012","volume":"76","author":"S Wang","year":"2023","unstructured":"Wang S, Zhang Y, Song F, Mao W (2023) A collaborative collision avoidance strategy for autonomous ships under mixed scenarios. J Navig 76:200\u2013224. https:\/\/doi.org\/10.1017\/S0373463323000012","journal-title":"J Navig"},{"key":"2116_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.116038","volume":"288","author":"K Liu","year":"2023","unstructured":"Liu K, Wu X, Zhou Y et al (2023) A conflict cluster-based method for collision avoidance decision-making in multi-ship encounter situations. Ocean Eng 288:116038. https:\/\/doi.org\/10.1016\/j.oceaneng.2023.116038","journal-title":"Ocean Eng"},{"key":"2116_CR4","doi-asserted-by":"publisher","first-page":"18433","DOI":"10.1109\/TITS.2022.3151826","volume":"23","author":"A Bakdi","year":"2022","unstructured":"Bakdi A, Vanem E (2022) Fullest COLREGs evaluation using fuzzy logic for collaborative decision-making analysis of autonomous ships in complex situations. IEEE Trans Intell Transport Syst 23:18433\u201318445. https:\/\/doi.org\/10.1109\/TITS.2022.3151826","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"2116_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.111917","volume":"260","author":"Z Du","year":"2022","unstructured":"Du Z, Negenborn RR, Reppa V (2022) COLREGS-Compliant collision avoidance for physically coupled multi-vessel systems with distributed MPC. Ocean Eng 260:111917. https:\/\/doi.org\/10.1016\/j.oceaneng.2022.111917","journal-title":"Ocean Eng"},{"key":"2116_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2022.108919","volume":"230","author":"J Zhang","year":"2023","unstructured":"Zhang J, Liu J, Hirdaris S et al (2023) An interpretable knowledge-based decision support method for ship collision avoidance using AIS data. Reliabil Eng Syst Saf 230:108919. https:\/\/doi.org\/10.1016\/j.ress.2022.108919","journal-title":"Reliabil Eng Syst Saf"},{"key":"2116_CR7","doi-asserted-by":"publisher","first-page":"754","DOI":"10.3390\/jmse8100754","volume":"8","author":"M Gao","year":"2020","unstructured":"Gao M, Shi G-Y (2020) Ship-collision avoidance decision-making learning of unmanned surface vehicles with automatic identification system data based on encoder-decoder automatic-response neural networks. JMSE 8:754. https:\/\/doi.org\/10.3390\/jmse8100754","journal-title":"JMSE"},{"key":"2116_CR8","doi-asserted-by":"publisher","first-page":"1084763","DOI":"10.3389\/fmars.2022.1084763","volume":"9","author":"C Wang","year":"2023","unstructured":"Wang C, Zhang X, Yang Z et al (2023) Collision avoidance for autonomous ship using deep reinforcement learning and prior-knowledge-based approximate representation. Front Mar Sci 9:1084763. https:\/\/doi.org\/10.3389\/fmars.2022.1084763","journal-title":"Front Mar Sci"},{"issue":"7964","key":"2116_CR9","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s41586-023-06004-9","volume":"618","author":"DJ Mankowitz","year":"2023","unstructured":"Mankowitz DJ, Michi A, Zhernov A, Gelmi M, Selvi M, Paduraru C, Silver D (2023) Faster sorting algorithms discovered using deep reinforcement learning. Nature 618(7964):257\u2013263. https:\/\/doi.org\/10.1038\/s41586-023-06004-9","journal-title":"Nature"},{"issue":"7976","key":"2116_CR10","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1038\/s41586-023-06419-4","volume":"620","author":"E Kaufmann","year":"2023","unstructured":"Kaufmann E, Bauersfeld L, Loquercio A, M\u00fcller M, Koltun V, Scaramuzza D (2023) Champion-level drone racing using deep reinforcement learning. Nature 620(7976):982\u2013987. https:\/\/doi.org\/10.1038\/s41586-023-06419-4","journal-title":"Nature"},{"issue":"7953","key":"2116_CR11","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1038\/s41586-023-05732-2","volume":"615","author":"S Feng","year":"2023","unstructured":"Feng S, Sun H, Yan X, Zhu H, Zou Z, Shen S, Liu HX (2023) Dense reinforcement learning for safety validation of autonomous vehicles. Nature 615(7953):620\u2013627. https:\/\/doi.org\/10.1038\/s41586-023-05732-2","journal-title":"Nature"},{"key":"2116_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120291","volume":"329","author":"Y Li","year":"2023","unstructured":"Li Y, Wang R, Li Y, Zhang M, Long C (2023) Wind power forecasting considering data privacy protection: a federated deep reinforcement learning approach. Appl Energy 329:120291. https:\/\/doi.org\/10.1016\/j.apenergy.2022.120291","journal-title":"Appl Energy"},{"issue":"1","key":"2116_CR13","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1038\/s41467-023-37139-y","volume":"14","author":"AA Volk","year":"2023","unstructured":"Volk AA, Epps RW, Yonemoto DT, Masters BS, Castellano FN, Reyes KG, Abolhasani M (2023) AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning. Nat Commun 14(1):1403. https:\/\/doi.org\/10.1038\/s41467-023-37139-y","journal-title":"Nat Commun"},{"key":"2116_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112378","volume":"264","author":"L Jiang","year":"2022","unstructured":"Jiang L, An L, Zhang X et al (2022) A human-like collision avoidance method for autonomous ship with attention-based deep reinforcement learning. Ocean Eng 264:112378. https:\/\/doi.org\/10.1016\/j.oceaneng.2022.112378","journal-title":"Ocean Eng"},{"key":"2116_CR15","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/s00773-020-00755-0","volume":"26","author":"R Sawada","year":"2021","unstructured":"Sawada R, Sato K, Majima T (2021) Automatic ship collision avoidance using deep reinforcement learning with LSTM in continuous action spaces. J Mar Sci Technol 26:509\u2013524. https:\/\/doi.org\/10.1007\/s00773-020-00755-0","journal-title":"J Mar Sci Technol"},{"key":"2116_CR16","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.apor.2019.02.020","volume":"86","author":"H Shen","year":"2019","unstructured":"Shen H, Hashimoto H, Matsuda A et al (2019) Automatic collision avoidance of multiple ships based on deep Q-learning. Appl Ocean Res 86:268\u2013288. https:\/\/doi.org\/10.1016\/j.apor.2019.02.020","journal-title":"Appl Ocean Res"},{"key":"2116_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2019.106436","volume":"191","author":"L Zhao","year":"2019","unstructured":"Zhao L, Roh M-I (2019) COLREGs-compliant multiship collision avoidance based on deep reinforcement learning. Ocean Eng 191:106436. https:\/\/doi.org\/10.1016\/j.oceaneng.2019.106436","journal-title":"Ocean Eng"},{"key":"2116_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.107001","volume":"199","author":"J Woo","year":"2020","unstructured":"Woo J, Kim N (2020) Collision avoidance for an unmanned surface vehicle using deep reinforcement learning. Ocean Eng 199:107001. https:\/\/doi.org\/10.1016\/j.oceaneng.2020.107001","journal-title":"Ocean Eng"},{"key":"2116_CR19","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.neucom.2020.05.089","volume":"411","author":"S Xie","year":"2020","unstructured":"Xie S, Chu X, Zheng M, Liu C (2020) A composite learning method for multi-ship collision avoidance based on reinforcement learning and inverse control. Neurocomputing 411:375\u2013392. https:\/\/doi.org\/10.1016\/j.neucom.2020.05.089","journal-title":"Neurocomputing"},{"key":"2116_CR20","doi-asserted-by":"publisher","first-page":"4055","DOI":"10.3390\/s19184055","volume":"19","author":"Wang Zhang","year":"2019","unstructured":"Zhang Wang, Liu Chen (2019) Decision-making for the autonomous navigation of maritime autonomous surface ships based on scene division and deep reinforcement learning. Sensors 19:4055. https:\/\/doi.org\/10.3390\/s19184055","journal-title":"Sensors"},{"key":"2116_CR21","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1007\/s13042-022-01713-5","volume":"14","author":"A Demir","year":"2023","unstructured":"Demir A, \u00c7ilden E, Polat F (2023) Landmark based guidance for reinforcement learning agents under partial observability. Int J Mach Learn Cyber 14:1543\u20131563. https:\/\/doi.org\/10.1007\/s13042-022-01713-5","journal-title":"Int J Mach Learn Cyber"},{"key":"2116_CR22","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1007\/s13042-021-01497-0","volume":"13","author":"C Zhang","year":"2022","unstructured":"Zhang C, Han Z, Liu B et al (2022) SCC-rFMQ: a multiagent reinforcement learning method in cooperative Markov games with continuous actions. Int J Mach Learn Cyber 13:1927\u20131944. https:\/\/doi.org\/10.1007\/s13042-021-01497-0","journal-title":"Int J Mach Learn Cyber"},{"key":"2116_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117602","volume":"304","author":"ZE Lee","year":"2021","unstructured":"Lee ZE, Zhang KM (2021) Generalized reinforcement learning for building control using behavioral cloning. Appl Energy 304:117602. https:\/\/doi.org\/10.1016\/j.apenergy.2021.117602","journal-title":"Appl Energy"},{"key":"2116_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-023-01976-6","author":"L Zhao","year":"2023","unstructured":"Zhao L, Chang T, Zhang L et al (2023) Multi-agent cooperation policy gradient method based on enhanced exploration for cooperative tasks. Int J Mach Learn Cyber. https:\/\/doi.org\/10.1007\/s13042-023-01976-6","journal-title":"Int J Mach Learn Cyber"},{"key":"2116_CR25","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1007\/s13042-021-01454-x","volume":"13","author":"M Hwang","year":"2022","unstructured":"Hwang M, Jiang W-C, Chen Y-J (2022) A critical state identification approach to inverse reinforcement learning for autonomous systems. Int J Mach Learn Cyber 13:1409\u20131423. https:\/\/doi.org\/10.1007\/s13042-021-01454-x","journal-title":"Int J Mach Learn Cyber"},{"key":"2116_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000086","volume":"16","author":"TM Moerland","year":"2023","unstructured":"Moerland TM, Broekens J, Plaat A, Jonker CM (2023) Model-based reinforcement learning: a survey. FNT Mach Learn 16:1\u2013118. https:\/\/doi.org\/10.1561\/2200000086","journal-title":"FNT Mach Learn"},{"key":"2116_CR27","doi-asserted-by":"publisher","first-page":"13344","DOI":"10.1109\/TPAMI.2023.3292075","volume":"45","author":"Z Zhu","year":"2023","unstructured":"Zhu Z, Lin K, Jain AK, Zhou J (2023) Transfer learning in deep reinforcement learning: a survey. IEEE Trans Pattern Anal Mach Intell 45:13344\u201313362. https:\/\/doi.org\/10.1109\/TPAMI.2023.3292075","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2116_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3305592","author":"R Yang","year":"2023","unstructured":"Yang R, Yan Z, Yang T, Wang Y, Ruichek Y (2023) Efficient online transfer learning for road participants detection in autonomous driving. IEEE Sens J. https:\/\/doi.org\/10.1109\/JSEN.2023.3305592","journal-title":"IEEE Sens J"},{"issue":"1","key":"2116_CR29","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/TVT.2021.3121985","volume":"71","author":"H Shu","year":"2021","unstructured":"Shu H, Liu T, Mu X, Cao D (2021) Driving tasks transfer using deep reinforcement learning for decision-making of autonomous vehicles in unsignalized intersection. IEEE Trans Veh Technol 71(1):41\u201352. https:\/\/doi.org\/10.1109\/TVT.2021.3121985","journal-title":"IEEE Trans Veh Technol"},{"issue":"4","key":"2116_CR30","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1111\/mice.12495","volume":"35","author":"S Chen","year":"2020","unstructured":"Chen S, Leng Y, Labi S (2020) A deep learning algorithm for simulating autonomous driving considering prior knowledge and temporal information. Comput Aided Civ Infrastruct Eng 35(4):305\u2013321. https:\/\/doi.org\/10.1111\/mice.12495","journal-title":"Comput Aided Civ Infrastruct Eng"},{"issue":"6","key":"2116_CR31","doi-asserted-by":"publisher","first-page":"3238","DOI":"10.1109\/TCYB.2020.2969025","volume":"51","author":"J Lin","year":"2020","unstructured":"Lin J, Liu HL, Tan KC, Gu F (2020) An effective knowledge transfer approach for multiobjective multitasking optimization. IEEE Trans Cybern 51(6):3238\u20133248. https:\/\/doi.org\/10.1109\/TCYB.2020.2969025","journal-title":"IEEE Trans Cybern"},{"issue":"10","key":"2116_CR32","doi-asserted-by":"publisher","first-page":"12719","DOI":"10.1007\/s10489-022-04148-1","volume":"53","author":"IG Daza","year":"2023","unstructured":"Daza IG, Izquierdo R, Mart\u00ednez LM, Benderius O, Llorca DF (2023) Sim-to-real transfer and reality gap modeling in model predictive control for autonomous driving. Appl Intell 53(10):12719\u201312735. https:\/\/doi.org\/10.1007\/s10489-022-04148-1","journal-title":"Appl Intell"},{"key":"2116_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08908-z","author":"X Zhang","year":"2023","unstructured":"Zhang X, Zheng K, Wang C et al (2023) A novel deep reinforcement learning for POMDP-based autonomous ship collision decision-making. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-023-08908-z","journal-title":"Neural Comput Appl"},{"key":"2116_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocecoaman.2023.106689","volume":"242","author":"K Zheng","year":"2023","unstructured":"Zheng K, Zhang X, Wang C et al (2023) A partially observable multi-ship collision avoidance decision-making model based on deep reinforcement learning. Ocean Coastal Manag 242:106689. https:\/\/doi.org\/10.1016\/j.ocecoaman.2023.106689","journal-title":"Ocean Coastal Manag"},{"key":"2116_CR35","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.ssci.2019.09.018","volume":"121","author":"Y Huang","year":"2020","unstructured":"Huang Y, Chen L, Chen P et al (2020) Ship collision avoidance methods: State-of-the-art. Saf Sci 121:451\u2013473. https:\/\/doi.org\/10.1016\/j.ssci.2019.09.018","journal-title":"Saf Sci"},{"key":"2116_CR36","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2022","unstructured":"Kiran BR, Sobh I, Talpaert V et al (2022) Deep reinforcement learning for autonomous driving: a survey. IEEE Trans Intell Transport Syst 23:4909\u20134926. https:\/\/doi.org\/10.1109\/TITS.2021.3054625","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"2116_CR37","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/s13042-022-01640-5","volume":"14","author":"Z Zhang","year":"2023","unstructured":"Zhang Z, Wu Z, Zhao H, Hu M (2023) Knowledge transfer based hierarchical few-shot learning via tree-structured knowledge graph. Int J Mach Learn Cyber 14:281\u2013294. https:\/\/doi.org\/10.1007\/s13042-022-01640-5","journal-title":"Int J Mach Learn Cyber"},{"key":"2116_CR38","doi-asserted-by":"publisher","first-page":"9764","DOI":"10.1126\/scirobotics.abb9764","volume":"5","author":"D-O Won","year":"2020","unstructured":"Won D-O, M\u00fcller K-R, Lee S-W (2020) An adaptive deep reinforcement learning framework enables curling robots with human-like performance in real-world conditions. Sci Robot 5:9764. https:\/\/doi.org\/10.1126\/scirobotics.abb9764","journal-title":"Sci Robot"},{"key":"2116_CR39","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Fran\u00e7ois-Lavet","year":"2018","unstructured":"Fran\u00e7ois-Lavet V, Henderson P, Islam R et al (2018) An introduction to deep reinforcement learning. FNT in Mach Learn 11:219\u2013354. https:\/\/doi.org\/10.1561\/2200000071","journal-title":"FNT in Mach Learn"},{"key":"2116_CR40","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"2116_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346","author":"X Wang","year":"2022","unstructured":"Wang X, Wang S, Liang X et al (2022) Deep reinforcement learning: a survey. IEEE Trans Neural Netw Learning Syst. https:\/\/doi.org\/10.1109\/TNNLS.2022.3207346","journal-title":"IEEE Trans Neural Netw Learning Syst"},{"key":"2116_CR42","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1109\/ICUS55513.2022.9986793","volume-title":"2022 IEEE Int Conf Unmanned Syst (ICUS)","author":"C Wang","year":"2022","unstructured":"Wang C, Zhang X, Gao H et al (2022) Efficient reinforcement learning for autonomous ship collision avoidance under learning experience reuse. 2022 IEEE Int Conf Unmanned Syst (ICUS). IEEE, Guangzhou, China, pp 1563\u20131568"},{"key":"2116_CR43","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1038\/s42256-022-00573-6","volume":"4","author":"H Ju","year":"2022","unstructured":"Ju H, Juan R, Gomez R et al (2022) Transferring policy of deep reinforcement learning from simulation to reality for robotics. Nat Mach Intell 4:1077\u20131087. https:\/\/doi.org\/10.1038\/s42256-022-00573-6","journal-title":"Nat Mach Intell"},{"key":"2116_CR44","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TEVC.2017.2664665","volume":"21","author":"Y Hou","year":"2017","unstructured":"Hou Y, Ong Y-S, Feng L, Zurada JM (2017) An evolutionary transfer reinforcement learning framework for multiagent systems. IEEE Trans Evol Computat 21:601\u2013615. https:\/\/doi.org\/10.1109\/TEVC.2017.2664665","journal-title":"IEEE Trans Evol Computat"},{"key":"2116_CR45","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.oceaneng.2017.05.029","volume":"140","author":"Y He","year":"2017","unstructured":"He Y, Jin Y, Huang L et al (2017) Quantitative analysis of COLREG rules and seamanship for autonomous collision avoidance at open sea. Ocean Eng 140:281\u2013291. https:\/\/doi.org\/10.1016\/j.oceaneng.2017.05.029","journal-title":"Ocean Eng"},{"key":"2116_CR46","doi-asserted-by":"publisher","first-page":"393","DOI":"10.2307\/3069463","volume":"44","author":"RJ Boland","year":"2001","unstructured":"Boland RJ, Singh J, Salipante P et al (2001) Knowledge representations and knowledge transfer. Acad Manag J 44:393\u2013417. https:\/\/doi.org\/10.2307\/3069463","journal-title":"Acad Manag J"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02116-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02116-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02116-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T08:19:39Z","timestamp":1723882779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02116-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,16]]},"references-count":46,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["2116"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02116-4","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,16]]},"assertion":[{"value":"13 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest:"}}]}}