{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T06:13:01Z","timestamp":1769753581479,"version":"3.49.0"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031360206","type":"print"},{"value":"9783031360213","type":"electronic"}],"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\/978-3-031-36021-3_30","type":"book-chapter","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T09:06:16Z","timestamp":1688115976000},"page":"298-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Solving Complex Sequential Decision-Making Problems by\u00a0Deep Reinforcement Learning with\u00a0Heuristic Rules"],"prefix":"10.1007","author":[{"given":"Thanh Thi","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Cuong M.","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Thien","family":"Huynh-The","sequence":"additional","affiliation":[]},{"given":"Quoc-Viet","family":"Pham","sequence":"additional","affiliation":[]},{"given":"Quoc Viet Hung","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[]},{"given":"Vijay Janapa","family":"Reddi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,26]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.neucom.2020.02.008","volume":"393","author":"Y Dong","year":"2020","unstructured":"Dong, Y., Tang, X., Yuan, Y.: Principled reward shaping for reinforcement learning via lyapunov stability theory. Neurocomputing 393, 83\u201390 (2020)","journal-title":"Neurocomputing"},{"key":"30_CR2","first-page":"15931","volume":"33","author":"Y Hu","year":"2020","unstructured":"Hu, Y., et al.: Learning to utilize shaping rewards: a new approach of reward shaping. Adv. Neural. Inf. Process. Syst. 33, 15931\u201315941 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR3","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1613\/jair.1.12412","volume":"69","author":"A Lazaridis","year":"2020","unstructured":"Lazaridis, A., Fachantidis, A., Vlahavas, I.: Deep reinforcement learning: a state-of-the-art walkthrough. J. Artif. Intell. Res. 69, 1421\u20131471 (2020)","journal-title":"J. Artif. Intell. Res."},{"key":"30_CR4","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"issue":"7540","key":"30_CR5","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"9","key":"30_CR6","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","volume":"50","author":"TT Nguyen","year":"2020","unstructured":"Nguyen, T.T., Nguyen, N.D., Nahavandi, S.: Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications. IEEE Trans. Cybern. 50(9), 3826\u20133839 (2020)","journal-title":"IEEE Trans. Cybern."},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1146\/annurev-control-100819-063206","volume":"3","author":"H Ravichandar","year":"2020","unstructured":"Ravichandar, H., Polydoros, A.S., Chernova, S., Billard, A.: Recent advances in robot learning from demonstration. Ann. Rev. Control Robot. Autonomous Syst. 3, 297\u2013330 (2020)","journal-title":"Ann. Rev. Control Robot. Autonomous Syst."},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Silva, A., Gombolay, M.: Encoding human domain knowledge to warm start reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 5042\u20135050 (2021)","DOI":"10.1609\/aaai.v35i6.16638"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Tajmajer, T.: Modular multi-objective deep reinforcement learning with decision values. In: 2018 Federated Conference on Computer Science and Information Systems (FedCSIS), pp. 85\u201393. IEEE (2018)","DOI":"10.15439\/2018F231"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: KoGuN: accelerating deep reinforcement learning via integrating human suboptimal knowledge. In: The 29th International Conference on International Joint Conferences on Artificial Intelligence, pp. 2291\u20132297 (2020)","DOI":"10.24963\/ijcai.2020\/317"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, R., Torabi, F., Guan, L., Ballard, D.H., Stone, P.: Leveraging human guidance for deep reinforcement learning tasks. In: The 28th International Joint Conference on Artificial Intelligence, pp. 6339\u20136346 (2019)","DOI":"10.24963\/ijcai.2019\/884"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-36021-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T09:09:48Z","timestamp":1688116188000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-36021-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031360206","9783031360213"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-36021-3_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"530","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"188","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,8","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}