{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T02:06:03Z","timestamp":1775873163988,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Centre for Artificial Intelligence and Robotics, Defense Research and Development Organization","award":["IITM\/DRDO\/VD\/324"],"award-info":[{"award-number":["IITM\/DRDO\/VD\/324"]}]},{"name":"Life Sciences Research Board DRDO, India","award":["IITM\/DRDO-LSRB\/VD\/301"],"award-info":[{"award-number":["IITM\/DRDO-LSRB\/VD\/301"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3117855","type":"journal-article","created":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T04:25:24Z","timestamp":1633407924000},"page":"138775-138790","source":"Crossref","is-referenced-by-count":14,"title":["Evaluation of Instance-Based Learning and Q-Learning Algorithms in Dynamic Environments"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0159-8780","authenticated-orcid":false,"given":"Anmol","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5735-5254","authenticated-orcid":false,"given":"Partha Pratim","family":"Roy","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":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001"},{"key":"ref38","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12181"},{"key":"ref32","article-title":"Instance-based decision-making model of repeated binary choice","author":"lebiere","year":"2007","journal-title":"Proc 8th Int Conf Cogn Modeling"},{"key":"ref31","first-page":"148","article-title":"Instance-based cognitive models of decision making","author":"gonzalez","year":"2005","journal-title":"Transfer of Knowledge in Economic Decision Making"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0018720812464045"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22348-8_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/bdm.722"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56991-8_32"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/tea.3660020306"},{"key":"ref1","author":"gross","year":"2015","journal-title":"Psychology The Science of Mind and Behavior"},{"key":"ref20","first-page":"848","article-title":"Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria","volume":"88","author":"erev","year":"1998","journal-title":"Amer Econ Rev"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0899-8256(05)80020-X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/game.2000.0841"},{"key":"ref24","article-title":"A theoretical analysis of deep Q-learning","author":"fan","year":"2019","journal-title":"arXiv 1901 00137"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4304\/jait.2.3.177-188"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MLDS.2017.13"},{"key":"ref50","first-page":"235","article-title":"Cognitive tutors: From the research classroom to all classrooms","author":"corbett","year":"2001","journal-title":"Technology Enhanced Learning Opportunities for Change"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3758\/BF03194060"},{"key":"ref52","first-page":"137","article-title":"Integrating visual and verbal knowledge during classroom learning with computer tutors","volume":"29","author":"butcher","year":"2007","journal-title":"Proc Annu Meeting Cognit Sci Soc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/sdr.4260100214"},{"key":"ref11","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771730"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-5127-0"},{"key":"ref13","author":"ravichandiran","year":"2018","journal-title":"Hands-On Reinforcement Learning with Python Master reinforcement and deep reinforcement learning using OpenAI Gym and TensorFlow"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22475-2_1"},{"key":"ref15","first-page":"417","article-title":"Machine learning annual review of computer science","volume":"4","author":"mitchell","year":"1990","journal-title":"J Comput Sci"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2704_2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1037\/a0024558"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2004.03.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/932485"},{"key":"ref3","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref5","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume":"6","author":"thomaz","year":"2006","journal-title":"Proc AAAI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-009-0345-0"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/978-94-017-9395-7_4","article-title":"Collaborative problem-solving tasks","author":"care","year":"2015","journal-title":"Assessment and Teaching of 21st Century Skills"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2012.02.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2004.02.014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF03354932"},{"key":"ref45","first-page":"242","article-title":"Social cognition: Memory decay and adaptive information filtering for robust information maintenance","volume":"1","author":"reitter","year":"2012","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/g2010136"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1006\/jmps.1999.1282"},{"key":"ref41","first-page":"361","article-title":"The central role of learning in cognition","author":"langley","year":"1981","journal-title":"Cognitive Skills and Their Acquisition"},{"key":"ref44","first-page":"1","article-title":"Implications of the ACT-R learning theory: No magic bullets","author":"anderson","year":"2000","journal-title":"Advances in Instructional Psychology Educational Design and Cognitive Science"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jarmac.2014.06.002"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09558862.pdf?arnumber=9558862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T00:41:01Z","timestamp":1699576861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9558862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3117855","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}