{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T01:11:01Z","timestamp":1782522661576,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2015,2,28]],"date-time":"2015-02-28T00:00:00Z","timestamp":1425081600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2015,11]]},"DOI":"10.1007\/s00521-015-1861-8","type":"journal-article","created":{"date-parts":[[2015,2,27]],"date-time":"2015-02-27T05:37:49Z","timestamp":1425015469000},"page":"1939-1954","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Topological Q-learning with internally guided exploration for mobile robot navigation"],"prefix":"10.1007","volume":"26","author":[{"given":"Muhammad Burhan","family":"Hafez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu Kiong","family":"Loo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,2,28]]},"reference":[{"issue":"4","key":"1861_CR1","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"RS Sutton","year":"1991","unstructured":"Sutton RS (1991) Dyna, an integrated architecture for learning, planning, and reacting. ACM SIGART Bull 2(4):160\u2013163","journal-title":"ACM SIGART Bull"},{"issue":"1","key":"1861_CR2","first-page":"103","volume":"13","author":"AW Moore","year":"1993","unstructured":"Moore AW, Atkeson CG (1993) Prioritized sweeping: reinforcement learning with less data and less time. Mach Learn 13(1):103\u2013130","journal-title":"Mach Learn"},{"key":"1861_CR3","doi-asserted-by":"crossref","unstructured":"Hwang KS, Jiang WC, Chen YJ (2012) Tree-based Dyna-Q agent. The 2012 IEEE\/ASME international conference on advanced intelligent mechatronics, Kaohsiung, Taiwan","DOI":"10.1109\/AIM.2012.6266001"},{"issue":"1","key":"1861_CR4","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton RS (1988) Learning to predict by the methods of temporal differences. Mach Learn 3(1):9\u201344","journal-title":"Mach Learn"},{"key":"1861_CR5","volume-title":"Learning from delayed rewards","author":"CGCH Watkins","year":"1989","unstructured":"Watkins CGCH (1989) Learning from delayed rewards. King\u2019s College, Cambridge"},{"issue":"1","key":"1861_CR6","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1023\/A:1007562800292","volume":"33","author":"M Wiering","year":"1998","unstructured":"Wiering M, Schmidhuber J (1998) Fast online Q(\u03bb). Mach Learn 33(1):105\u2013115","journal-title":"Mach Learn"},{"key":"1861_CR7","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237\u2013285","journal-title":"J Artif Intell Res"},{"issue":"1\u20133","key":"1861_CR8","first-page":"283","volume":"22","author":"J Peng","year":"1996","unstructured":"Peng J, Williams RJ (1996) Incremental multi-step Q-learning. Mach Learn 22(1\u20133):283\u2013290","journal-title":"Mach Learn"},{"issue":"3\u20134","key":"1861_CR9","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/S0921-8890(97)00042-0","volume":"22","author":"CF Touzet","year":"1997","unstructured":"Touzet CF (1997) Neural reinforcement learning for behaviour synthesis. Rob Auton Syst 22(3\u20134):251\u2013281","journal-title":"Rob Auton Syst"},{"issue":"3","key":"1861_CR10","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/37.588194","volume":"17","author":"M Zeller","year":"1997","unstructured":"Zeller M, Sharma R, Schulten K (1997) Motion planning of a pneumatic robot using a neural network. IEEE Control Syst 17(3):89\u201398","journal-title":"IEEE Control Syst"},{"key":"1861_CR11","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","volume-title":"Reinforcement learning and dynamic programming using function approximators","author":"L Busoniu","year":"2010","unstructured":"Busoniu L, Babuska R, Schutter BD, Ernst D (2010) Reinforcement learning and dynamic programming using function approximators. CRC Press, New York"},{"issue":"2\u20133","key":"1861_CR12","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1023\/A:1017988514716","volume":"49","author":"JDR Mill\u00e1n","year":"2002","unstructured":"Mill\u00e1n JDR, Posenato D, Dedieu E (2002) Continuous-action Q-learning. Mach Learn 49(2\u20133):247\u2013265","journal-title":"Mach Learn"},{"key":"1861_CR13","first-page":"623","volume":"1","author":"R Munos","year":"2008","unstructured":"Munos R, Szepesv\u00e1ri C (2008) Finite-time bounds for fitted value iteration. J Mach Learn Res 1:623\u2013665","journal-title":"J Mach Learn Res"},{"key":"1861_CR14","doi-asserted-by":"crossref","unstructured":"Dietterich TG (2000) Hierarchical reinforcement learning with the MAXQ value function decomposition. Artificial intelligence research","DOI":"10.1613\/jair.639"},{"key":"1861_CR15","doi-asserted-by":"crossref","DOI":"10.1109\/SCIS-ISIS.2012.6505358","volume-title":"Multi-scale Q-learning of a mobile robot in dynamic environments","author":"N Takase","year":"2012","unstructured":"Takase N, Kubota N, Baba N (2012) Multi-scale Q-learning of a mobile robot in dynamic environments. SCIS-ISIS, Kobe"},{"key":"1861_CR16","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1007\/s00521-003-0385-9","volume":"12","author":"APS Braga","year":"2003","unstructured":"Braga APS, Ara\u00fajo AFR (2003) A topological reinforcement learning agent for navigation. Neural Comput Appl 12:220\u2013236","journal-title":"Neural Comput Appl"},{"issue":"1\u20133","key":"1861_CR17","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.neucom.2006.07.010","volume":"70","author":"APS Braga","year":"2006","unstructured":"Braga APS, Ara\u00fajo AFR (2006) Influence Zones: a strategy to enhance reinforcement learning. Neurocomputing 70(1\u20133):21\u201334","journal-title":"Neurocomputing"},{"key":"1861_CR18","unstructured":"Dai P, Strehl AL, J. Goldsmith (2008) Expediting RL by using graphical structures. Proceedings of the seventh international joint conference on autonomous agents and multiagent systems"},{"key":"1861_CR19","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Introduction to reinforcement learning. MIT Press\/Bradford Books, Cambridge"},{"key":"1861_CR20","doi-asserted-by":"crossref","unstructured":"Sutton RS (1990) Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. Proceedings of the seventh international conference on machine learning","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"1861_CR21","doi-asserted-by":"crossref","unstructured":"Luciw M, Graziano V, Ring M, Schmidhuber J (2011) Artificial curiosity with planning for autonomous perceptual and cognitive development. Development and learning (ICDL), Frankfurt","DOI":"10.1109\/DEVLRN.2011.6037356"},{"key":"1861_CR22","doi-asserted-by":"crossref","unstructured":"Zahedi K, Martius G, Ay N (2013) Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis. Front Psychol. doi: 10.3389\/fpsyg.2013.00801","DOI":"10.3389\/fpsyg.2013.00801"},{"issue":"1","key":"1861_CR23","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/S0004-3702(03)00114-0","volume":"152","author":"E Remolina","year":"2004","unstructured":"Remolina E, Kuipers B (2004) Towards a general theory of topological maps. Artif Intell 152(1):47\u2013104","journal-title":"Artif Intell"},{"key":"1861_CR24","unstructured":"Thrun S, Buckenz A (1996) Integrating grid-based and topological maps for mobile robot navigation. Proceedings of the thirteenth national conference on artificial intelligence AAAI, Portland, Oregon"},{"key":"1861_CR25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-88163-3","volume-title":"Self-organization and associative memory","author":"T Kohonen","year":"1989","unstructured":"Kohonen T (1989) Self-organization and associative memory. Springer, Berlin"},{"key":"1861_CR26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-56927-2","volume-title":"Self-organizing maps","author":"T Kohonen","year":"2001","unstructured":"Kohonen T (2001) Self-organizing maps. Springer, Berlin"},{"key":"1861_CR27","first-page":"397","volume-title":"A neural-gas network learns topologies","author":"T Martinetz","year":"1991","unstructured":"Martinetz T, Schulten K (1991) A neural-gas network learns topologies. Artif Neural Netw, Amsterdam, pp 397\u2013402"},{"key":"1861_CR28","first-page":"625","volume":"7","author":"B Fritzke","year":"1995","unstructured":"Fritzke B (1995) A growing neural gas network learns topologies. Adv Neural Inf Process Syst 7:625\u2013632","journal-title":"Adv Neural Inf Process Syst"},{"key":"1861_CR29","doi-asserted-by":"crossref","unstructured":"Jockusch J, Ritter H (1999) An Instantaneous Topological Mapping Model for correlated stimuli. Proceedings of the IJCNN\u201999, Washington, DC","DOI":"10.1109\/IJCNN.1999.831553"},{"key":"1861_CR30","unstructured":"Ng AY, Jordan M (2000) PEGASUS: a policy search method for large MDPs and POMDPs. Proceedings of the sixteenth conference on uncertainty in artificial intelligence, San Francisco"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-015-1861-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-015-1861-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-015-1861-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T09:47:57Z","timestamp":1566380877000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-015-1861-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,28]]},"references-count":30,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2015,11]]}},"alternative-id":["1861"],"URL":"https:\/\/doi.org\/10.1007\/s00521-015-1861-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,2,28]]}}}