{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T17:13:48Z","timestamp":1782234828135,"version":"3.54.5"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T00:00:00Z","timestamp":1626912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T00:00:00Z","timestamp":1626912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"FAPESP-IBM","award":["7\/07833-9"],"award-info":[{"award-number":["7\/07833-9"]}]},{"name":"FAPESP-IBM","award":["2016\/18792-9"],"award-info":[{"award-number":["2016\/18792-9"]}]},{"DOI":"10.13039\/501100002322","name":"CAPES","doi-asserted-by":"crossref","award":["001"],"award-info":[{"award-number":["001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10489-021-02423-1","type":"journal-article","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T18:02:45Z","timestamp":1626976965000},"page":"4488-4510","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Heuristics, Answer Set Programming and Markov Decision Process for Solving a Set of Spatial Puzzles*"],"prefix":"10.1007","volume":"52","author":[{"given":"Thiago Freitas","family":"dos Santos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8484-0354","authenticated-orcid":false,"given":"Paulo E.","family":"Santos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonardo Anjoletto","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reinaldo A. C.","family":"Bianchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro","family":"Cabalar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,22]]},"reference":[{"issue":"3","key":"2423_CR1","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1162\/neco.1989.1.3.295","volume":"1","author":"HB Barlow","year":"1989","unstructured":"Barlow HB (1989) Unsupervised learning. Neural computation 1(3):295\u2013311","journal-title":"Neural computation"},{"key":"2423_CR2","unstructured":"Bellman RE, Dreyfus SE (2015) Applied dynamic programming. Princeton University Press"},{"issue":"2","key":"2423_CR3","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10732-007-9031-5","volume":"14","author":"RA Bianchi","year":"2008","unstructured":"Bianchi RA, Ribeiro CH, Costa AH (2008) Accelerating autonomous learning by using heuristic selection of actions. Journal of Heuristics 14(2):135\u2013168","journal-title":"Journal of Heuristics"},{"key":"2423_CR4","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/s10846-017-0731-2","volume":"91","author":"RA Bianchi","year":"2018","unstructured":"Bianchi RA, Santos PE, da Silva IJ, Celiberto LA, de Mantaras RL (2018) Heuristically accelerated reinforcement learning by means of case-based reasoning and transfer learning. Journal of Intelligent & Robotic Systems 91:301\u2013312","journal-title":"Journal of Intelligent & Robotic Systems"},{"key":"2423_CR5","doi-asserted-by":"crossref","unstructured":"Bianchi\u00a0RAC,\u00a0Ribeiro\u00a0CHC,\u00a0Costa\u00a0AHR (2004) Heuristically accelerated q-learning: a new approach to speed up reinforcement learning. In: Bazzan\u00a0 ALC, Labidi\u00a0S\u00a0(eds)\u00a0Advances in Artificial Intelligence \u2013 SBIA.\u00a0Springer, Berlin Heidelberg,\u00a0p 245\u2013254","DOI":"10.1007\/978-3-540-28645-5_25"},{"issue":"12","key":"2423_CR6","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1145\/2043174.2043195","volume":"54","author":"G Brewka","year":"2011","unstructured":"Brewka G, Eiter T, Truszczy\u0144ski M (2011) Answer set programming at a glance. Communications of the ACM 54(12):92\u2013103","journal-title":"Communications of the ACM"},{"key":"2423_CR7","unstructured":"Cabalar P (2017) Notas de aula"},{"issue":"1","key":"2423_CR8","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.artint.2010.04.004","volume":"175","author":"P Cabalar","year":"2011","unstructured":"Cabalar P, Santos PE (2011) Formalising the fisherman\u2019s folly puzzle. Artificial Intelligence 175(1):346\u2013377","journal-title":"Artificial Intelligence"},{"key":"2423_CR9","doi-asserted-by":"crossref","unstructured":"Cabalar\u00a0P,\u00a0Santos\u00a0PE (2016) A qualitative spatial representation of string loops as holes. In: Artificial intelligence, vol 238. Elsevier,\u00a0pp 1\u201310","DOI":"10.1016\/j.artint.2016.05.001"},{"key":"2423_CR10","doi-asserted-by":"publisher","first-page":"39273","DOI":"10.1109\/ACCESS.2020.2976121","volume":"8","author":"L Cai","year":"2020","unstructured":"Cai L, Sun Q, Xu T, Ma Y, Chen Z (2020) Multi-auv collaborative target recognition based on transfer-reinforcement learning. IEEE Access 8:39273\u201339284","journal-title":"IEEE Access"},{"key":"2423_CR11","unstructured":"Celiberto\u00a0LA Jr, Matsuura JP, De\u00a0Mantaras RL, Bianchi RA (2011)\u00a0Using cases as heuristics in reinforcement learning: a transfer learning application. In:\u00a0IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol 22, pp 1211"},{"key":"2423_CR12","series-title":"pp","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/978-3-030-24268-8_51","volume-title":"Artificial Intelligence and Security","author":"X Chen","year":"2019","unstructured":"Chen X, Chen J, Chen Y, Yang J, Li D (2019) Heuristic-q: A privacy data pricing method based on heuristic reinforcement learning. In: Sun X, Pan Z, Bertino E (eds) Artificial Intelligence and Security. pp. Springer International Publishing, Cham, pp 553\u2013565"},{"key":"2423_CR13","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/S1574-6526(07)03013-1","volume":"3","author":"AG Cohn","year":"2008","unstructured":"Cohn AG, Renz J (2008) Qualitative spatial representation and reasoning. Foundations of Artificial Intelligence 3:551\u2013596","journal-title":"Foundations of Artificial Intelligence"},{"key":"2423_CR14","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1613\/jair.1.11396","volume":"64","author":"FL Da Silva","year":"2019","unstructured":"Da Silva FL, Costa AHR (2019) A survey on transfer learning for multiagent reinforcement learning systems. Journal of Artificial Intelligence Research 64:645\u2013703","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2423_CR15","doi-asserted-by":"crossref","unstructured":"Da\u00a0Silva FL, Taylor ME, Costa AHR (2018)\u00a0Autonomously reusing knowledge in multiagent reinforcement learning. In:\u00a0IJCAI, pp 5487\u20135493","DOI":"10.24963\/ijcai.2018\/774"},{"key":"2423_CR16","doi-asserted-by":"crossref","unstructured":"dos Santos TF, Santos P, Ferreira L, Bianchi R, Cabalar P (2018)\u00a0Solving a spatial puzzle using answer set programming integrated with markov decision process. In:\u00a02018 7th Brazilian Conference on Intelligent Systems (BRACIS), pp 528\u2013533","DOI":"10.1109\/BRACIS.2018.00097"},{"key":"2423_CR17","unstructured":"dos Santos TF, Santos PE, Ferreira LA, Bianchi RAC, Cabalar P (2019)\u00a0Heuristics, answer set programming and markov decision process for solving a set of spatial puzzles. CoRR, abs\/1903.03411"},{"key":"2423_CR18","unstructured":"Dutra AR,\u00a0Garcez ASd (2017)\u00a0A comparison between deep q-networks and deep symbolic reinforcement learning"},{"key":"2423_CR19","doi-asserted-by":"crossref","unstructured":"Dylla F, Lee JH, Mossakowski T, Schneider T, Delden AV, Ven JVD,\u00a0Wolter D (2017)\u00a0A survey of qualitative spatial and temporal calculi: algebraic and computational properties. ACM Comput Surv 50(1):7:1\u20137:39","DOI":"10.1145\/3038927"},{"key":"2423_CR20","doi-asserted-by":"crossref","unstructured":"Eiter T, Ianni G, Krennwallner T (2009) Answer set programming: A primer. Reasoning Web. Semantic Technologies for Information Systems. Springer, Berlin, Heidelberg, pp 40\u2013110","DOI":"10.1007\/978-3-642-03754-2_2"},{"issue":"4\u20135","key":"2423_CR21","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1017\/S1471068413000525","volume":"13","author":"E Erdem","year":"2013","unstructured":"Erdem E, Patoglu V, Saribatur ZG, Sch\u00fcller P, Uras T (2013) Finding optimal plans for multiple teams of robots through a mediator: A logic-based approach. Theory and Practice of Logic Programming 13(4\u20135):831\u2013846","journal-title":"Theory and Practice of Logic Programming"},{"key":"2423_CR22","unstructured":"Even-dar E, Kakade SM,\u00a0Mansour Y (2005)\u00a0Experts in a markov decision process. In: Saul LK, Weiss Y, Bottou L\u00a0(eds)\u00a0Advances in Neural Information Processing Systems 17. MIT Press, pp 401\u2013408"},{"issue":"3","key":"2423_CR23","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1287\/moor.1090.0396","volume":"34","author":"E Even-Dar","year":"2009","unstructured":"Even-Dar E, Kakade SM, Mansour Y (2009) Online markov decision processes. Mathematics of Operations Research 34(3):726\u2013736","journal-title":"Mathematics of Operations Research"},{"issue":"4","key":"2423_CR24","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s10489-017-0988-y","volume":"47","author":"LA Ferreira","year":"2017","unstructured":"Ferreira LA, Bianchi RA, Santos PE, de Mantaras RL (2017) Answer set programming for non-stationary markov decision processes. Applied Intelligence 47(4):993\u20131007","journal-title":"Applied Intelligence"},{"key":"2423_CR25","doi-asserted-by":"crossref","unstructured":"Ferreira LA, Bianchi RAdC, Santos PE, De\u00a0Mantaras RL (2018)\u00a0A method for the online construction of the set of states of a markov decision process using answer set programming. In: Recent trends and future technology in applied intelligence. Springer International Publishing,\u00a0pp 3\u201315","DOI":"10.1007\/978-3-319-92058-0_1"},{"issue":"4","key":"2423_CR26","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s10489-017-0988-y","volume":"47","author":"LA Ferreira","year":"2017","unstructured":"Ferreira LA, Bianchi RAC, Santos PE, de Mantaras RL (2017) Answer set programming for non-stationary markov decision processes. Applied Intelligence 47(4):993\u20131007","journal-title":"Applied Intelligence"},{"key":"2423_CR27","unstructured":"Garcez Ad, Dutra ARR, Alonso E (2018)\u00a0Towards symbolic reinforcement learning with common sense. arXiv preprint arXiv:1804.08597"},{"key":"2423_CR28","doi-asserted-by":"crossref","unstructured":"Garnelo\u00a0M, Shanahan\u00a0M (2019)\u00a0Reconciling deep learning with symbolic artificial intelligence: representing objects and relations. Current Opinion in Behavioral Sciences\u00a029:17\u201323","DOI":"10.1016\/j.cobeha.2018.12.010"},{"key":"2423_CR29","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/S1574-6526(07)03007-6","volume":"3","author":"M Gelfond","year":"2008","unstructured":"Gelfond M (2008) Answer sets. Foundations of Artificial Intelligence 3:285\u2013316","journal-title":"Foundations of Artificial Intelligence"},{"key":"2423_CR30","first-page":"1070","volume":"88","author":"M Gelfond","year":"1988","unstructured":"Gelfond M, Lifschitz V (1988) The stable model semantics for logic programming. ICLP\/SLP 88:1070\u20131080","journal-title":"ICLP\/SLP"},{"key":"2423_CR31","unstructured":"Gelfond\u00a0M, Lifschitz V (1998)\u00a0Action languages"},{"key":"2423_CR32","unstructured":"Gelfond M, Rushton N (2010)\u00a0Causal and probabilistic reasoning in p-log. Heuristics, probabilities and causality. A tribute to Judea Pearl, pp 337\u2013359"},{"key":"2423_CR33","doi-asserted-by":"crossref","unstructured":"Glatt R, Da Silva FL, da Costa Bianchi RA, Costa AHR (2020)\u00a0Decaf: deep case-based policy inference for knowledge transfer in reinforcement learning. Expert Syst Appl\u00a0156:113420","DOI":"10.1016\/j.eswa.2020.113420"},{"key":"2423_CR34","doi-asserted-by":"crossref","unstructured":"Hass J, Lagarias JC, Pippenger N (1999)\u00a0The computational complexity of knot and link problems. J ACM\u00a046(2):185\u2013211","DOI":"10.1145\/301970.301971"},{"key":"2423_CR35","doi-asserted-by":"crossref","unstructured":"Hastie T, Tibshirani R, Friedman J (2009)\u00a0Overview of supervised learning. In:\u00a0The elements of statistical learning. Springer,\u00a0pp 9\u201341","DOI":"10.1007\/978-0-387-84858-7_2"},{"key":"2423_CR36","doi-asserted-by":"crossref","unstructured":"Hoffman KL, Padberg M, Rinaldi G (2013)\u00a0Traveling salesman problem. Springer US, Boston, MA,\u00a0pp 1573\u20131578","DOI":"10.1007\/978-1-4419-1153-7_1068"},{"key":"2423_CR37","doi-asserted-by":"crossref","unstructured":"Homem TPD,\u00a0Santos PE, Reali Costa AH, da Costa Bianchi RA, Lopez de Mantaras R (2020)\u00a0Qualitative case-based reasoning and learning. Artif Intell\u00a0283:103258","DOI":"10.1016\/j.artint.2020.103258"},{"key":"2423_CR38","doi-asserted-by":"crossref","unstructured":"Hu R, Andreas J, Rohrbach M, Darrell T, Saenko K (2017)\u00a0Learning to reason: end-to-end module networks for visual question answering. arXiv preprint arXiv:1704.05526","DOI":"10.1109\/ICCV.2017.93"},{"key":"2423_CR39","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1609\/icaps.v30i1.6750","volume":"30","author":"L Illanes","year":"2020","unstructured":"Illanes L, Yan X, Icarte RT, McIlraith SA (2020) Symbolic plans as high-level instructions for reinforcement learning. Proceedings of the International Conference on Automated Planning and Scheduling 30:540\u2013550","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"issue":"1","key":"2423_CR40","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s13218-016-0480-6","volume":"31","author":"G Kern-Isberner","year":"2017","unstructured":"Kern-Isberner G, Lukasiewicz T (2017) Many facets of reasoning under uncertainty, inconsistency, vagueness, and preferences: A brief survey. KI - K\u00fcnstliche Intelligenz 31(1):9\u201313","journal-title":"KI - K\u00fcnstliche Intelligenz"},{"key":"2423_CR41","doi-asserted-by":"crossref","unstructured":"Khandelwal P, Yang F, Leonetti M, Lifschitz V, Stone P (2014)\u00a0Planning in action language bc while learning action costs for mobile robots. In: ICAPS","DOI":"10.1609\/icaps.v24i1.13671"},{"issue":"1","key":"2423_CR42","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TCYB.2014.2319733","volume":"45","author":"ML Koga","year":"2015","unstructured":"Koga ML, Freire V, Costa AH (2015) Stochastic abstract policies: Generalizing knowledge to improve reinforcement learning. IEEE Transactions on Cybernetics 45(1):77\u201388","journal-title":"IEEE Transactions on Cybernetics"},{"key":"2423_CR43","doi-asserted-by":"crossref","unstructured":"Kowalski\u00a0R,\u00a0Sergot M (1989)\u00a0A logic-based calculus of events. In:\u00a0Foundations of knowledge base management. Springer,\u00a0pp 23\u201355","DOI":"10.1007\/978-3-642-83397-7_2"},{"key":"2423_CR44","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.artint.2016.07.004","volume":"241","author":"M Leonetti","year":"2016","unstructured":"Leonetti M, Iocchi L, Stone P (2016) A synthesis of automated planning and reinforcement learning for efficient, robust decision-making. Artificial Intelligence 241:103\u2013130","journal-title":"Artificial Intelligence"},{"key":"2423_CR45","unstructured":"Licks GP, Couto JC, de\u00a0F\u00e1tima\u00a0Miehe P, De\u00a0Paris R, Ruiz DD, Meneguzzi F (2020)\u00a0Smartix: a database indexing agent based on reinforcement learning. Appl Intell 1\u201314"},{"key":"2423_CR46","unstructured":"Lifschitz V (2008)\u00a0What is answer set programming?. In:\u00a0Proceedings of the AAAI Conference on Artificial Intelligence, vol 8. MIT Press,\u00a0pp 1594\u20131597"},{"key":"2423_CR47","doi-asserted-by":"crossref","unstructured":"Ligozat G (2013) Qualitative spatial and temporal reasoning. John Wiley & Sons","DOI":"10.1002\/9781118601457"},{"key":"2423_CR48","doi-asserted-by":"crossref","unstructured":"Liu T, Huang B, Deng Z, Wang H, Tang X, Wang X,\u00a0Cao D (2020)\u00a0Heuristics-oriented overtaking decision making for autonomous vehicles using reinforcement learning. IET Electrical Systems in Transportation","DOI":"10.1049\/iet-est.2020.0044"},{"key":"2423_CR49","doi-asserted-by":"crossref","unstructured":"Lomonaco V, Desai K, Culurciello E, Maltoni D (2020)\u00a0Continual reinforcement learning in 3D non-stationary environments. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"2423_CR50","unstructured":"Lu K, Zhang S, Stone P, Chen X (2018)\u00a0Robot representation and reasoning with knowledge from reinforcement learning. arXiv preprint arXiv:1809.11074"},{"key":"2423_CR51","doi-asserted-by":"crossref","unstructured":"Martins\u00a0MF,\u00a0Bianchi\u00a0RA (2014)\u00a0Heuristically-accelerated reinforcement learning: a comparative analysis of performance. In:\u00a0Conference towards autonomous robotic systems. Springer, Berlin, Heidelberg,\u00a0pp 15\u201327","DOI":"10.1007\/978-3-662-43645-5_2"},{"issue":"12","key":"2423_CR52","doi-asserted-by":"publisher","first-page":"1030","DOI":"10.1145\/33447.33448","volume":"30","author":"J McCarthy","year":"1987","unstructured":"McCarthy J (1987) Generality in artificial intelligence. Communications of the ACM 30(12):1030\u20131035","journal-title":"Communications of the ACM"},{"key":"2423_CR53","unstructured":"McCarthy J (1998) Elaboration tolerance. In: Common sense, vol 98"},{"issue":"7540","key":"2423_CR54","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"2423_CR55","doi-asserted-by":"publisher","first-page":"2771","DOI":"10.1109\/ACCESS.2015.2507158","volume":"3","author":"N Morozs","year":"2015","unstructured":"Morozs N, Clarke T, Grace D (2015) Heuristically accelerated reinforcement learning for dynamic secondary spectrum sharing. IEEE Access 3:2771\u20132783","journal-title":"IEEE Access"},{"key":"2423_CR56","unstructured":"Murugesan K, Atzeni M, Kapanipathi P, Shukla P, Kumaravel S, Tesauro G,\u00a0Talamadupula K, Sachan M, Campbell M (2020)\u00a0Text-based rl agents with commonsense knowledge: new challenges, environments and baselines. arXiv preprint arXiv:2010.03790"},{"key":"2423_CR57","doi-asserted-by":"crossref","unstructured":"Nickles\u00a0M (2011)\u00a0Integrating relational reinforcement learning with reasoning about actions and change. In: International conference on inductive logic programming. Springer,\u00a0pp 255\u2013269","DOI":"10.1007\/978-3-642-31951-8_23"},{"key":"2423_CR58","doi-asserted-by":"crossref","unstructured":"Nickles M (2012)\u00a0A system for the use of answer set programming in reinforcement learning. In:\u00a0Logics in artificial intelligence. Springer, Berlin, Heidelberg,\u00a0pp 488\u2013491","DOI":"10.1007\/978-3-642-33353-8_40"},{"issue":"11","key":"2423_CR59","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1007\/s10489-020-01758-5","volume":"50","author":"S Padakandla","year":"2020","unstructured":"Padakandla S, Prabuchandran K, Bhatnagar S (2020) Reinforcement learning algorithm for non-stationary environments. Applied Intelligence 50(11):3590\u20133606","journal-title":"Applied Intelligence"},{"key":"2423_CR60","unstructured":"Rettinger A, Hagemann A, Nickles M (2014)\u00a0Learning an optimal sequence of questions for the disambiguation of queries over structured data. In:\u00a0Workshops at the twenty-eighth AAAI conference on artificial intelligence"},{"key":"2423_CR61","unstructured":"Santoro A, Raposo D, Barrett DG, Malinowski M, Pascanu R, Battaglia\u00a0P,\u00a0Lillicrap T (2017)\u00a0A simple neural network module for relational reasoning. arXiv preprint arXiv:1706.01427"},{"key":"2423_CR62","unstructured":"Santos\u00a0PE, Cabalar P (2007)\u00a0Holes, knots and shapes: A spatial ontology of a puzzle. In:\u00a0AAAI Spring symposium: logical formalizations of commonsense reasoning, pp 144\u2013149"},{"key":"2423_CR63","unstructured":"Santos PE, Cabalar P (2013)\u00a0An investigation of actions, change, space within a hole-loop dichotomy. In:\u00a0Proc. of the 11th Intl. Symp. on Logical Formalizations of Commonsense Reasoning (Commonsense\u201313), Ayia Napa, Cyprus"},{"issue":"1","key":"2423_CR64","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1080\/13875868.2015.1091837","volume":"16","author":"PE Santos","year":"2016","unstructured":"Santos PE, Cabalar P (2016) Framing holes within a loop hierarchy. Spatial Cognition & Computation 16(1):54\u201395","journal-title":"Spatial Cognition & Computation"},{"issue":"4","key":"2423_CR65","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1080\/13875868.2019.1667998","volume":"19","author":"PE Santos","year":"2019","unstructured":"Santos PE, Cabalar P, Casati R (2019) The knowledge of knots: an interdisciplinary literature review. Spatial Cognition & Computation 19(4):334\u2013358","journal-title":"Spatial Cognition & Computation"},{"key":"2423_CR66","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1613\/jair.1.11524","volume":"65","author":"M Sridharan","year":"2019","unstructured":"Sridharan M, Gelfond M, Zhang S, Wyatt J (2019) Reba: A refinement-based architecture for knowledge representation and reasoning in robotics. Journal of Artificial Intelligence Research 65:87\u2013180","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2423_CR67","doi-asserted-by":"crossref","unstructured":"Stock O (1998)\u00a0Spatial and temporal reasoning. Springer Science & Business Media","DOI":"10.1007\/978-0-585-28322-7"},{"key":"2423_CR68","unstructured":"Sutton\u00a0RS, Barto AG (2018)\u00a0Reinforcement learning: an introduction. MIT press"},{"key":"2423_CR69","doi-asserted-by":"crossref","unstructured":"Taylor A, Dusparic I, L\u00f3pez EG, Clarke S, Cahill V (2014)\u00a0Accelerating learning in multi-objective systems through transfer learning. In:\u00a0IJCNN. Citeseer, pp 2298\u20132305","DOI":"10.1109\/IJCNN.2014.6889438"},{"key":"2423_CR70","unstructured":"Thielscher M (1998)\u00a0Introduction to the fluent calculus"},{"key":"2423_CR71","unstructured":"Topin N, Haltmeyer N, Squire S, Winder J, desJardins M,\u00a0MacGlashan\u00a0J (2015)\u00a0Portable option discovery for automated learning transfer in object-oriented markov decision processes. In: IJCAI, pp 3856\u20133864"},{"key":"2423_CR72","unstructured":"Van\u00a0Otterlo M (2009)\u00a0The logic of adaptive behavior. In:\u00a0Knowledge representation"},{"issue":"2","key":"2423_CR73","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1017\/S1471068416000193","volume":"17","author":"PA Wa\u0142\u0119ga","year":"2017","unstructured":"Wa\u0142\u0119ga PA, Schultz C, Bhatt M (2017) Non-monotonic spatial reasoning with answer set programming modulo theories. Theory and Practice of Logic Programming 17(2):205\u2013225","journal-title":"Theory and Practice of Logic Programming"},{"issue":"3\u20134","key":"2423_CR74","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins CJ, Dayan P (1992) Q-learning. Machine learning 8(3\u20134):279\u2013292","journal-title":"Q-learning. Machine learning"},{"key":"2423_CR75","unstructured":"Wikipedia contributors (2019) Q-learning \u2014 Wikipedia, the free encyclopedia. [Online; accessed 21-November-2019]"},{"key":"2423_CR76","unstructured":"Wu\u00a0Y,\u00a0Tian Y (2016)\u00a0Training agent for first-person shooter game with actor-critic curriculum learning"},{"key":"2423_CR77","unstructured":"Xiaomei H, Jun X, Jianfei C (2019)\u00a0Robot path planning based on an improved q-learning method. In: International Computer Science and Applications Conference (ICSAC 2019), pp 99\u2013102."},{"key":"2423_CR78","doi-asserted-by":"crossref","unstructured":"Yang F, Khandelwal P, Leonetti M, Stone P (2014)\u00a0Planning in answer set programming while learning action costs for mobile robots. In AAAI Spring 2014 symposium on knowledge representation and reasoning in robotics (AAAI-SSS)","DOI":"10.1609\/icaps.v24i1.13671"},{"key":"2423_CR79","doi-asserted-by":"crossref","unstructured":"Yang F, Lyu D, Liu B, Gustafson S (2018)\u00a0Peorl: integrating symbolic planning and hierarchical reinforcement learning for robust decision-making. In:\u00a0Proceedings of the 27th International Joint Conference on Artificial Intelligence,\u00a0IJCAI\u201918. AAAI Press,\u00a0pp 4860\u20134866","DOI":"10.24963\/ijcai.2018\/675"},{"issue":"3","key":"2423_CR80","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1287\/moor.1090.0397","volume":"34","author":"JY Yu","year":"2009","unstructured":"Yu JY, Mannor S, Shimkin N (2009) Markov decision processes with arbitrary reward processes. Mathematics of Operations Research 34(3):737\u2013757","journal-title":"Mathematics of Operations Research"},{"issue":"1","key":"2423_CR81","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1515\/pjbr-2018-0026","volume":"9","author":"MA Zamani","year":"2018","unstructured":"Zamani MA, Magg S, Weber C, Wermter S, Fu D (2018) Deep reinforcement learning using compositional representations for performing instructions. Paladyn, Journal of Behavioral Robotics 9(1):358\u2013373","journal-title":"Paladyn, Journal of Behavioral Robotics"},{"issue":"3","key":"2423_CR82","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s11571-017-9423-7","volume":"11","author":"F Zhang","year":"2017","unstructured":"Zhang F, Duan S, Wang L (2017) Route searching based on neural networks and heuristic reinforcement learning. Cognitive neurodynamics 11(3):245\u2013258","journal-title":"Cognitive neurodynamics"},{"key":"2423_CR83","doi-asserted-by":"publisher","first-page":"109301","DOI":"10.1109\/ACCESS.2019.2933454","volume":"7","author":"G Zhang","year":"2019","unstructured":"Zhang G, Li Y, Xu X, Dai H (2019) Efficient training techniques for multi-agent reinforcement learning in combat tasks. IEEE Access 7:109301\u2013109310","journal-title":"IEEE Access"},{"issue":"3","key":"2423_CR84","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TRO.2015.2422531","volume":"31","author":"S Zhang","year":"2015","unstructured":"Zhang S, Sridharan M, Wyatt JL (2015) Mixed logical inference and probabilistic planning for robots in unreliable worlds. IEEE Transactions on Robotics 31(3):699\u2013713","journal-title":"IEEE Transactions on Robotics"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02423-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02423-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02423-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T06:19:43Z","timestamp":1672899583000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02423-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,22]]},"references-count":84,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["2423"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02423-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,22]]},"assertion":[{"value":"8 April 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}