{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:51:34Z","timestamp":1769633494729,"version":"3.49.0"},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/ssci.2016.7849365","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T17:24:33Z","timestamp":1487265873000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["A hierarchical maze navigation algorithm with Reinforcement Learning and mapping"],"prefix":"10.1109","author":[{"given":"Tommaso","family":"Mannucci","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik-Jan","family":"van Kampen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1986.1087032"},{"key":"ref11","article-title":"Feudal Reinforcement Learning","author":"dayan","year":"1993","journal-title":"Advances in Neural Inform Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087316"},{"key":"ref13","first-page":"944","article-title":"Integrating Grid-Based and Topological Maps for Mobile Robot Navigation","author":"thrun","year":"1996","journal-title":"Proc AAAI Nat Conf Artificial Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref15","article-title":"Autonomous Navigation in Partially Observable Environments","author":"zhou","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref6","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1998","journal-title":"Advances in Neural Inform Process Syst"},{"key":"ref5","author":"precup","year":"2000","journal-title":"Temporal Abstraction in Reinforcement Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2008.921541"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"Hierarchical reinforcement learning with the MAXQ value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"J Artificial Intell Res"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement Learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artificial Intell Res"},{"key":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","first-page":"948","article-title":"A hierarchical reinforcement learning based control architecture for semi-autonomous rescue robots in cluttered environments","author":"barzin","year":"2010","journal-title":"2010 IEEE Conf Auto Sci Eng"}],"event":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Athens, Greece","start":{"date-parts":[[2016,12,6]]},"end":{"date-parts":[[2016,12,9]]}},"container-title":["2016 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7840087\/7849361\/07849365.pdf?arnumber=7849365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T15:57:10Z","timestamp":1568822230000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7849365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/ssci.2016.7849365","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}