{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T02:22:28Z","timestamp":1773368548513,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"ARC","award":["LP130100743"],"award-info":[{"award-number":["LP130100743"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1109\/tciaig.2017.2658659","type":"journal-article","created":{"date-parts":[[2017,1,25]],"date-time":"2017-01-25T19:52:25Z","timestamp":1485373945000},"page":"91-96","source":"Crossref","is-referenced-by-count":6,"title":["Learning Options From Demonstrations: A <italic>Pac-Man<\/italic> Case Study"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6567-1380","authenticated-orcid":false,"given":"Marco","family":"Tamassia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4133-7913","authenticated-orcid":false,"given":"Fabio","family":"Zambetta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William L.","family":"Raffe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Mueller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"278","article-title":"Policy\n invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"0","journal-title":"Proc 6th Int Conf Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36755-1_25"},{"key":"ref11","first-page":"506","article-title":"Policyblocks: An algorithm for creating useful macro-actions in reinforcement learning","author":"pickett","year":"0","journal-title":"Proc 19th Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015355"},{"key":"ref13","first-page":"95","article-title":"Using relative novelty to identify useful temporal abstractions in reinforcement\n learning","author":"?im?ek","year":"0","journal-title":"Proc 21st Int Conf Mach Learn"},{"key":"ref14","first-page":"816","article-title":"Identifying useful subgoals in reinforcement learning by local graph partitioning","author":"?im?ek","year":"0","journal-title":"Proc 22nd Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/11840541_30"},{"key":"ref16","first-page":"2259","article-title":"Causal graph based decomposition of factored MDPs","volume":"7","author":"jonsson","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390238"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2050205"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553529"},{"key":"ref28","first-page":"1885","article-title":"Teaching introductory artificial intelligence with Pac-Man","author":"denero","year":"0","journal-title":"Proc Symp Edu Adv Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref27","first-page":"42","article-title":"Gnu parallel - the command-line power tool","volume":"36","author":"tange","year":"2011","journal-title":"LOGIN The USENIX Magazine"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref29","author":"cormen","year":"2001","journal-title":"Introduction to Algorithms"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3"},{"key":"ref8","first-page":"361","article-title":"Automatic discovery of subgoals in reinforcement learning using diverse density","author":"mcgovern","year":"0","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref7","first-page":"299","article-title":"The utility\n of temporal abstraction in reinforcement learning","author":"jong","year":"0","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref2","first-page":"28","article-title":"Knightcap:\n A chess programm that learns by combining TD(lambda) with game-tree search","author":"baxter","year":"0","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45622-8_16"},{"key":"ref1","first-page":"537","article-title":"Scaling reinforcement learning toward robocup soccer","author":"stone","year":"0","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref20","first-page":"1162","article-title":"Constructing skill trees for\n reinforcement learning agents from demonstration trajectories","author":"konidaris","year":"2010","journal-title":"Advances in Neural Information Processing Systems 23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa3799"},{"key":"ref21","article-title":"Learning\n options through human interaction","author":"subramanian","year":"0","journal-title":"IJCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT-IJCAI)"},{"key":"ref24","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14803-8_18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2011.37"},{"key":"ref25","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/8318012\/07833121.pdf?arnumber=7833121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:23:40Z","timestamp":1642004620000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7833121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":30,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tciaig.2017.2658659","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3]]}}}