{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:39:26Z","timestamp":1742960366329,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031712524"},{"type":"electronic","value":"9783031712531"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-71253-1_2","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T12:01:49Z","timestamp":1727524909000},"page":"16-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Framework of\u00a0Reinforcement Learning for\u00a0Truncated L\u00e9vy Flight Exploratory"],"prefix":"10.1007","author":[{"given":"Quan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shile","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixian","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"issue":"15","key":"2_CR1","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.ifacol.2022.07.619","volume":"55","author":"P Osinenko","year":"2022","unstructured":"Osinenko, P., Dobriborsci, D., Aumer, W.: Reinforcement learning with guarantees: a review. IFAC-PapersOnLine 55(15), 123\u2013128 (2022)","journal-title":"IFAC-PapersOnLine"},{"key":"2_CR2","unstructured":"Wang, X., et\u00a0al.: SCC: an efficient deep reinforcement learning agent mastering the game of starcraft ii. In: International Conference on Machine Learning, pp. 10905\u201310915. PMLR (2021)"},{"key":"2_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103569","volume":"125","author":"AA Apolinarska","year":"2021","unstructured":"Apolinarska, A.A., Pacher, M., Li, H., Cote, N., Pastrana, R., Gramazio, F., Kohler, M.: Robotic assembly of timber joints using reinforcement learning. Autom. Constr. 125, 103569 (2021)","journal-title":"Autom. Constr."},{"key":"2_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110975","volume":"149","author":"Y Song","year":"2023","unstructured":"Song, Y., Suganthan, P.N., Pedrycz, W., Ou, J., He, Y., Chen, Y., Wu, Y.: Ensemble reinforcement learning: a survey. Appl. Soft Comput. 149, 110975 (2023)","journal-title":"Appl. Soft Comput."},{"key":"2_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120493","volume":"229","author":"MJ Kim","year":"2023","unstructured":"Kim, M.J., Kim, J.S., Ahn, C.W.: Evolving population method for real-time reinforcement learning. Expert Syst. Appl. 229, 120493 (2023)","journal-title":"Expert Syst. Appl."},{"key":"2_CR6","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"2_CR7","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355 (2018)"},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/978-3-642-40988-2_15","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"E Contal","year":"2013","unstructured":"Contal, E., Buffoni, D., Robicquet, A., Vayatis, N.: Parallel gaussian process optimization with upper confidence bound and pure exploration. In: Blockeel, H., Kersting, K., Nijssen, S., \u017delezn\u00fd, F. (eds.) ECML PKDD 2013. LNCS (LNAI), vol. 8188, pp. 225\u2013240. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40988-2_15"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Yang, X.S.: Metaheuristic optimization: nature-inspired algorithms and applications. In: Artificial Intelligence, Evolutionary Computing and Metaheuristics: In the Footsteps of Alan Turing, pp. 405\u2013420. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-29694-9_16","DOI":"10.1007\/978-3-642-29694-9_16"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Tasfi, N., Capretz, M.: Noisy importance sampling actor-critic: an off-policy actor-critic with experience replay. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207681"},{"issue":"6","key":"2_CR11","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.1214\/aoms\/1177699147","volume":"37","author":"LE Baum","year":"1966","unstructured":"Baum, L.E., Petrie, T.: Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37(6), 1554\u20131563 (1966)","journal-title":"Ann. Math. Stat."},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.matcom.2022.08.017","volume":"204","author":"Q He","year":"2023","unstructured":"He, Q., Liu, H., Ding, G., Liangping, T.: A modified l\u00e9vy flight distribution for solving high-dimensional numerical optimization problems. Math. Comput. Simul. 204, 376\u2013400 (2023)","journal-title":"Math. Comput. Simul."},{"key":"2_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2022.101207","volume":"75","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Chen, Y., Ding, S., Liang, D., He, H.: A novel particle swarm optimization algorithm with l\u00e9vy flight and orthogonal learning. Swarm Evol. Comput. 75, 101207 (2022)","journal-title":"Swarm Evol. Comput."},{"key":"2_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-46429-8_1","volume-title":"Computer Performance Evaluation.Modelling Techniques and Tools","author":"ME Crovella","year":"2000","unstructured":"Crovella, M.E.: Performance evaluation with heavy tailed distributions. In: Haverkort, B.R., Bohnenkamp, H.C., Smith, C.U. (eds.) TOOLS 2000. LNCS, vol. 1786, pp. 1\u20139. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-46429-8_1"},{"key":"2_CR15","unstructured":"Einstan, A.A.: On the movement of small particles suspended in stationary liquids required by the molecular-kinetic theory of heat. Phys. (Leipzig) 17, 549 (1905)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Syberfeldt, A., Lidberg, S.: Real-world simulation-based manufacturing optimization using cuckoo search. In: Proceedings of the 2012 Winter Simulation Conference (WSC), pp. 1\u201312. IEEE (2012)","DOI":"10.1109\/WSC.2012.6465158"},{"issue":"22","key":"2_CR17","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1103\/PhysRevLett.73.2946","volume":"73","author":"RN Mantegna","year":"1994","unstructured":"Mantegna, R.N., Stanley, H.E.: Stochastic process with ultraslow convergence to a Gaussian: the truncated l\u00e9vy flight. Phys. Rev. Lett. 73(22), 2946 (1994)","journal-title":"Phys. Rev. Lett."},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"2_CR19","unstructured":"Sharma, S., Srinivas, A., Ravindran, B.: Learning to repeat: fine grained action repetition for deep reinforcement learning. arXiv preprint arXiv:1702.06054 (2017)"}],"container-title":["IFIP Advances in Information and Communication Technology","Intelligence Science V"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-71253-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T12:01:55Z","timestamp":1727524915000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-71253-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031712524","9783031712531"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-71253-1_2","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligence Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cs.njust.edu.cn\/icis2024\/main.psp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}