{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:33Z","timestamp":1774455333805,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031431289","type":"print"},{"value":"9783031431296","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\/978-3-031-43129-6_19","type":"book-chapter","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T05:02:14Z","timestamp":1694754134000},"page":"189-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Modeling Human Actions in\u00a0the\u00a0Cart-Pole Game Using Cognitive and\u00a0Deep Reinforcement Learning Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6312-8947","authenticated-orcid":false,"given":"Aadhar","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5171-5546","authenticated-orcid":false,"given":"Mahavir","family":"Dabas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2601-2125","authenticated-orcid":false,"given":"Shashank","family":"Uttrani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0229-0289","authenticated-orcid":false,"given":"Sakshi","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2151-8314","authenticated-orcid":false,"given":"Varun","family":"Dutt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,16]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, J., Bothell, D., Byrne, M., Douglass, S., Lebiere, C., Qin, Y.: An integrated theory of mind. Psychol. Rev. 111, 1036\u20131060 (2004)","DOI":"10.1037\/0033-295X.111.4.1036"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: A brief survey of deep reinforcement learning. arXiv preprint arXiv:1708.05866 (2017)","DOI":"10.1109\/MSP.2017.2743240"},{"key":"19_CR3","doi-asserted-by":"publisher","unstructured":"Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. SMC-13(5), 834\u2013846 (1983). https:\/\/doi.org\/10.1109\/TSMC.1983.6313077","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"19_CR4","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/978-3-030-36150-1_22","volume-title":"Robot 2019: Fourth Iberian Robotics Conference","author":"FF Duarte","year":"2020","unstructured":"Duarte, F.F., Lau, N., Pereira, A., Reis, L.P.: Benchmarking deep and non-deep reinforcement learning algorithms for discrete environments. In: Silva, M.F., Lu\u00eds Lima, J., Reis, L.P., Sanfeliu, A., Tardioli, D. (eds.) ROBOT 2019. AISC, vol. 1093, pp. 263\u2013275. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-36150-1_22"},{"key":"19_CR5","unstructured":"Fgadaleta: top 4 reasons why reinforcement learning sucks (ep. 83) (2019). https:\/\/datascienceathome.com\/what-is-wrong-with-reinforcement-learning\/"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Gonzalez, C., Dutt, V.: Instance-based learning models of training. In: Proceedings of the human factors and ergonomics society annual meeting, vol. 54, pp. 2319\u20132323. SAGE Publications Sage CA: Los Angeles, CA (2010)","DOI":"10.1177\/154193121005402721"},{"key":"19_CR7","unstructured":"Kotseruba, I., Tsotsos, J.K.: A review of 40 years of cognitive architecture research: core cognitive abilities and practical applications. arXiv preprint arXiv:1610.08602 (2016)"},{"key":"19_CR8","unstructured":"Kumar, S.: Balancing a cartpole system with reinforcement learning-a tutorial. arXiv preprint arXiv:2006.04938 (2020)"},{"key":"19_CR9","unstructured":"Meltzer, B., Michie, D.: Machine intelligence 4 (1970)"},{"key":"19_CR10","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Mothanna, Y., Hewahi, N.: Review on reinforcement learning in cartpole game. In: 2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), pp. 344\u2013349. IEEE (2022)","DOI":"10.1109\/3ICT56508.2022.9990767"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Nagendra, S., Podila, N., Ugarakhod, R., George, K.: Comparison of reinforcement learning algorithms applied to the Cart-Pole problem. In: 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 26\u201332. IEEE (2017)","DOI":"10.1109\/ICACCI.2017.8125811"},{"issue":"6","key":"19_CR14","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/S1364-6613(99)01327-3","volume":"3","author":"S Schaal","year":"1999","unstructured":"Schaal, S.: Is imitation learning the route to humanoid robots? Trends Cogn. Sci. 3(6), 233\u2013242 (1999)","journal-title":"Trends Cogn. Sci."},{"key":"19_CR15","unstructured":"Sunden, P.: Q-learning and deep Q-learning in OpenAI gym cartpole classic control environment (2022)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Surriani, A., Wahyunggoro, O., Cahyadi, A.I.: Reinforcement learning for cart pole inverted pendulum system. In: 2021 IEEE Industrial Electronics and Applications Conference (IEACon), pp. 297\u2013301. IEEE (2021)","DOI":"10.1109\/IEACon51066.2021.9654440"},{"key":"19_CR17","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction MIT press. Cambridge, MA 22447 (1998)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Tan, Z., Karakose, M.: Optimized deep reinforcement learning approach for dynamic system. In: 2020 IEEE International Symposium on Systems Engineering (ISSE), pp. 1\u20134. IEEE (2020)","DOI":"10.1109\/ISSE49799.2020.9272245"},{"issue":"6","key":"19_CR19","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/TNNLS.2019.2927227","volume":"31","author":"X Wang","year":"2019","unstructured":"Wang, X., Gu, Y., Cheng, Y., Liu, A., Chen, C.P.: Approximate policy-based accelerated deep reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 31(6), 1820\u20131830 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"19_CR20","doi-asserted-by":"publisher","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992). https:\/\/doi.org\/10.1007\/BF00992698","DOI":"10.1007\/BF00992698"}],"container-title":["Lecture Notes in Computer Science","Social, Cultural, and Behavioral Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43129-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:31:15Z","timestamp":1710261075000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43129-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031431289","9783031431296"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43129-6_19","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":"16 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SBP-BRiMS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pittsburgh, PA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"20 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sbp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.sbp-brims.org","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":"73","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":"31","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":"0","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":"42% - 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":"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":"3","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)"}}]}}