{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T01:34:04Z","timestamp":1769304844774,"version":"3.49.0"},"publisher-location":"Cham","reference-count":9,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031479939","type":"print"},{"value":"9783031479946","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\/978-3-031-47994-6_26","type":"book-chapter","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T08:02:28Z","timestamp":1699344148000},"page":"266-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Q-Learning: Solutions for Grid World Problem with Forward and Backward Reward Propagations"],"prefix":"10.1007","author":[{"given":"Snobin","family":"Antony","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghi","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaxin","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,8]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Campbell, J.S., Givigi, S.N., Schwartz, H.M.: Multiple-model Q-learning for stochastic reinforcement delays. In: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. Institute of Electrical and Electronics Engineers Inc, pp. 1611\u20131617 (2014)","DOI":"10.1109\/SMC.2014.6974146"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schomaker, L., Wiering, M.: An investigation into the effect of the learning rate on overestimation bias of connectionist q-learning. In: ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence. SciTePress, pp. 107\u2013118 (2021)","DOI":"10.5220\/0010227301070118"},{"key":"26_CR3","unstructured":"Coggan, M.: Exploration and Exploitation in Reinforcement Learning"},{"key":"26_CR4","unstructured":"IEEE Computational Intelligence Society, International Neural Network Society, Institute of Electrical and Electronics Engineers, IEEE World Congress on Computational Intelligence (2020\u202f: Online) 2020 International Joint Conference on Neural Networks (IJCNN)\u202f: 2020 conference proceedings"},{"key":"26_CR5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/4235.728210","volume":"2","author":"WG Macready","year":"1998","unstructured":"Macready, W.G., Wolpert, D.H.: Bandit problems and the exploration\/exploitation tradeoff. IEEE Trans. Evol. Comput. 2, 2\u201322 (1998). https:\/\/doi.org\/10.1109\/4235.728210","journal-title":"IEEE Trans. Evol. Comput."},{"key":"26_CR6","unstructured":"Manju, M.S., Punithavalli, M.M.: An Analysis of Q-Learning Algorithms with Strategies of Reward Function"},{"key":"26_CR7","doi-asserted-by":"publisher","first-page":"209320","DOI":"10.1109\/ACCESS.2020.3038605","volume":"8","author":"M Naeem","year":"2020","unstructured":"Naeem, M., Rizvi, S.T.H., Coronato, A.: A Gentle introduction to reinforcement learning and its application in different fields. IEEE Access 8, 209320\u2013209344 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3038605","journal-title":"IEEE Access"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Tijsma, A.D., Drugan, M.M., Wiering, M.A.: Comparing exploration strategies for Q-learning in random stochastic mazes. In: 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc. (2017)","DOI":"10.1109\/SSCI.2016.7849366"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Yen, G., Yang, F., Hickey, T., Goldstein, M.: Coordination of exploration and exploitation in a dynamic environment. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1014\u20131018 (2001)","DOI":"10.1109\/IJCNN.2001.939499"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XL"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47994-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T14:28:31Z","timestamp":1730471311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47994-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031479939","9783031479946"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47994-6_26","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":"8 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SGAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovative Techniques and Applications of Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"12 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2023\/","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":"ConferenceExpert","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"27","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":"20","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":"40% - 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 or 3","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":"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)"}},{"value":"A total of 76 reviewers plus two \u2018executive program committees\u2019 (one for each stream)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}