{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:57:13Z","timestamp":1743145033723,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031184604"},{"type":"electronic","value":"9783031184611"}],"license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-18461-1_27","type":"book-chapter","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T07:15:14Z","timestamp":1665558914000},"page":"393-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to\u00a0Solve Sequential Planning Problems Without Rewards"],"prefix":"10.1007","author":[{"given":"Chris","family":"Robinson","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"issue":"3","key":"27_CR1","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1287\/moor.16.3.580","volume":"16","author":"DP Bertsekas","year":"1991","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: An analysis of stochastic shortest path problems. Math. Oper. Res. 16(3), 580\u2013595 (1991)","journal-title":"Math. Oper. Res."},{"issue":"1\u20132","key":"27_CR2","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/S0004-3702(96)00047-1","volume":"90","author":"AL Blum","year":"1997","unstructured":"Blum, A.L., Furst, M.L.: Fast planning through planning graph analysis. Artif. Intell. 90(1\u20132), 281\u2013300 (1997)","journal-title":"Artif. Intell."},{"key":"27_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/10720246_25","volume-title":"Recent Advances in AI Planning","author":"AL Blum","year":"2000","unstructured":"Blum, A.L., Langford, J.C.: Probabilistic planning in the graphplan framework. In: Biundo, S., Fox, M. (eds.) Probabilistic planning in the graphplan framework. LNCS (LNAI), vol. 1809, pp. 319\u2013332. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/10720246_25"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Dimitrov, N.B., Morton, D.P.: Combinatorial design of a stochastic markov decision process. In: Operations Research and Cyber-Infrastructure (2009)","DOI":"10.1007\/978-0-387-88843-9_9"},{"key":"27_CR5","unstructured":"Grzes, M.: Reward shaping in episodic reinforcement learning (2017)"},{"issue":"1","key":"27_CR6","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.ejor.2018.10.052","volume":"285","author":"M Guillot","year":"2020","unstructured":"Guillot, M., Stauffer, G.: The stochastic shortest path problem: a polyhedral combinatorics perspective. Eur. J. Oper. Res. 285(1), 148\u2013158 (2020)","journal-title":"Eur. J. Oper. Res."},{"key":"27_CR7","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1613\/jair.5483","volume":"60","author":"J Hostetler","year":"2017","unstructured":"Hostetler, J., Fern, A., Dietterich, T.: Sample-based tree search with fixed and adaptive state abstractions. J. Artif. Intell. Res. 60, 717\u2013777 (2017)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR8","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1613\/jair.5393","volume":"59","author":"A Hunter","year":"2017","unstructured":"Hunter, A., Thimm, M.: Probabilistic reasoning with abstract argumentation frameworks. J. Artif. Intell. Res. 59, 565\u2013611 (2017)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"27_CR9","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/BF00114729","volume":"22","author":"S Koenig","year":"1996","unstructured":"Koenig, S., Simmons, R.G.: The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms. Mach. Learn. 22(1), 227\u2013250 (1996)","journal-title":"Mach. Learn."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Kolobov, A., Mausam, M., Weld, D.S., Geffner, H.: Heuristic search for generalized stochastic shortest path mdps. In: Twenty-First International Conference on Automated Planning and Scheduling (2011)","DOI":"10.1609\/icaps.v21i1.13452"},{"key":"27_CR11","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1613\/jair.5575","volume":"61","author":"G Konidaris","year":"2018","unstructured":"Konidaris, G., Kaelbling, L.P., Lozano-Perez, T., Learning symbolic representations for abstract high-level planning: From skills to symbols. J. Artif. Intell. Res. 61, 215\u2013289 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR12","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.: A synthesis of automated planning and reinforcement learning for efficient, robust decision-making. Artif. Intell. 241, 103\u2013130 (2016)","journal-title":"Artif. Intell."},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1613\/jair.1.11261","volume":"63","author":"S L\u00fcdtke","year":"2018","unstructured":"L\u00fcdtke, S., Schr\u00f6der, M., Kr\u00fcger, F., Bader, S., Kirste, T.: State-space abstractions for probabilistic inference: a systematic review. J. Artif. Intell. Res. 63, 789\u2013848 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1007\/11840817_87","volume-title":"Artificial Neural Networks \u2013 ICANN 2006","author":"L Matignon","year":"2006","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Reward function and initial values: better choices for accelerated goal-directed reinforcement learning. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 840\u2013849. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11840817_87"},{"key":"27_CR15","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1613\/jair.1.11569","volume":"65","author":"L Pineda","year":"2019","unstructured":"Pineda, L., Zilberstein, S.: Probabilistic planning with reduced models. J. Artif. Intell. Res. 65, 271\u2013306 (2019)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR16","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1613\/jair.5153","volume":"57","author":"M Steinmetz","year":"2016","unstructured":"Steinmetz, M., Hoffmann, J., Buffet, O.: Goal probability analysis in probabilistic planning: exploring and enhancing the state of the art. J. Artif. Intell. Res. 57, 229\u2013271 (2016)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR17","unstructured":"Szepesv\u00e1ri, C., Littman, M.L.: Generalized markov decision processes: Dynamic-programming and reinforcement-learning algorithms. In: Proceedings of International Conference of Machine Learning, vol.\u00a096 (1996)"}],"container-title":["Lecture Notes in Networks and Systems","Proceedings of the Future Technologies Conference (FTC) 2022, Volume 1"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18461-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T07:23:44Z","timestamp":1665559424000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18461-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"ISBN":["9783031184604","9783031184611"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18461-1_27","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022,10,13]]},"assertion":[{"value":"13 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FTC 2022","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of the Future Technologies Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ftc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/FTC","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}