{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:46:55Z","timestamp":1742914015315,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030937355"},{"type":"electronic","value":"9783030937362"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-93736-2_58","type":"book-chapter","created":{"date-parts":[[2022,2,17]],"date-time":"2022-02-17T21:02:28Z","timestamp":1645131748000},"page":"819-829","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference"],"prefix":"10.1007","author":[{"given":"Mohamed","family":"Baioumy","sequence":"first","affiliation":[]},{"given":"Bruno","family":"Lacerda","sequence":"additional","affiliation":[]},{"given":"Paul","family":"Duckworth","sequence":"additional","affiliation":[]},{"given":"Nick","family":"Hawes","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,17]]},"reference":[{"key":"58_CR1","unstructured":"Attias, H.: Planning by probabilistic inference. In: AISTATS (2003)"},{"issue":"3","key":"58_CR2","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."},{"key":"58_CR3","doi-asserted-by":"crossref","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-dynamic programming: an overview. In: Proceedings of 1995 34th IEEE Conference on Decision and Control, vol. 1, pp. 560\u2013564. IEEE (1995)","DOI":"10.1109\/CDC.1995.478953"},{"key":"58_CR4","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/S0004-3702(01)00129-1","volume":"134","author":"M Campbell","year":"2002","unstructured":"Campbell, M., Hoane, A.J., Hsu, F.: Deep blue. Artif. Intell. 134, 57\u201383 (2002)","journal-title":"Artif. Intell."},{"key":"58_CR5","unstructured":"Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms. MIT Press (2009)"},{"key":"58_CR6","unstructured":"Crites, R.H., Barto, A.G., et al.: Improving elevator performance using reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 1017\u20131023 (1996)"},{"key":"58_CR7","doi-asserted-by":"crossref","unstructured":"Da Costa, L., Parr, T., Sajid, N., Veselic, S., Neacsu, V., Friston, K.: Active inference on discrete state-spaces: a synthesis. arXiv preprint arXiv:2001.07203 (2020)","DOI":"10.1016\/j.jmp.2020.102447"},{"key":"58_CR8","unstructured":"Da Costa, L., Sajid, N., Parr, T., Friston, K., Smith, R.: The relationship between dynamic programming and active inference: The discrete, finite-horizon case. arXiv preprint arXiv:2009.08111 (2020)"},{"issue":"1","key":"58_CR9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1287\/mnsc.10.1.98","volume":"10","author":"F d\u2019Epenoux","year":"1963","unstructured":"d\u2019Epenoux, F.: A probabilistic production and inventory problem. Manage. Sci. 10(1), 98\u2013108 (1963)","journal-title":"Manage. Sci."},{"key":"58_CR10","unstructured":"Duckworth, P., Lacerda, B., Hawes, N.: Time-bounded mission planning in time-varying domains with semi-mdps and gaussian processes (2021)"},{"key":"58_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-540-71209-1_6","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"K Etessami","year":"2007","unstructured":"Etessami, K., Kwiatkowska, M., Vardi, M.Y., Yannakakis, M.: Multi-objective model checking of Markov decision processes. In: Grumberg, O., Huth, M. (eds.) TACAS 2007. LNCS, vol. 4424, pp. 50\u201365. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-71209-1_6"},{"key":"58_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-642-21455-4_3","volume-title":"Formal Methods for Eternal Networked Software Systems","author":"V Forejt","year":"2011","unstructured":"Forejt, V., Kwiatkowska, M., Norman, G., Parker, D.: Automated verification techniques for probabilistic systems. In: Bernardo, M., Issarny, V. (eds.) SFM 2011. LNCS, vol. 6659, pp. 53\u2013113. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21455-4_3"},{"issue":"1","key":"58_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/NECO_a_00912","volume":"29","author":"K Friston","year":"2017","unstructured":"Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., Pezzulo, G.: Active inference: a process theory. Neural Comput. 29(1), 1\u201349 (2017)","journal-title":"Neural Comput."},{"key":"58_CR14","doi-asserted-by":"crossref","unstructured":"Grondman, I., Busoniu, L., Lopes, G.A., Babuska, R.: A survey of actor-critic reinforcement learning: standard and natural policy gradients. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 42(6), 1291\u20131307 (2012)","DOI":"10.1109\/TSMCC.2012.2218595"},{"issue":"4","key":"58_CR15","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s00422-018-0753-2","volume":"112","author":"R Kaplan","year":"2018","unstructured":"Kaplan, R., Friston, K.J.: Planning and navigation as active inference. Biol. Cybern. 112(4), 323\u2013343 (2018). https:\/\/doi.org\/10.1007\/s00422-018-0753-2","journal-title":"Biol. Cybern."},{"key":"58_CR16","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)"},{"key":"58_CR17","doi-asserted-by":"crossref","unstructured":"Kolobov, A.: Planning with Markov Decision Processes: An AI Perspective, vol. 6. Morgan & Claypool Publishers, San Rafael (2012)","DOI":"10.2200\/S00426ED1V01Y201206AIM017"},{"key":"58_CR18","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1613\/jair.4649","volume":"53","author":"A Kumar","year":"2015","unstructured":"Kumar, A., Zilberstein, S., Toussaint, M.: Probabilistic inference techniques for scalable multiagent decision making. J. Artif. Intell. Res. 53, 223\u2013270 (2015)","journal-title":"J. Artif. Intell. Res."},{"issue":"9","key":"58_CR19","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1177\/0278364919856695","volume":"38","author":"B Lacerda","year":"2019","unstructured":"Lacerda, B., Faruq, F., Parker, D., Hawes, N.: Probabilistic planning with formal performance guarantees for mobile service robots. Int. J. Robot. Res. 38(9), 1098\u20131123 (2019)","journal-title":"Int. J. Robot. Res."},{"key":"58_CR20","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-64919-7_1","volume-title":"Active Inference","author":"B Millidge","year":"2020","unstructured":"Millidge, B., Tschantz, A., Seth, A.K., Buckley, C.L.: On the relationship between active inference and control as inference. In: IWAI 2020. CCIS, vol. 1326, pp. 3\u201311. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64919-7_1"},{"key":"58_CR21","unstructured":"Murphy, K.P.: Machine Learning: A Probabilistic Perspective. MIT Press, Massachusetts (2012)"},{"issue":"1","key":"58_CR22","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/0167-6377(86)90094-5","volume":"5","author":"JL Nazareth","year":"1986","unstructured":"Nazareth, J.L., Kulkarni, R.B.: Linear programming formulations of Markov decision processes. Oper. Res. Lett. 5(1), 13\u201316 (1986)","journal-title":"Oper. Res. Lett."},{"key":"58_CR23","doi-asserted-by":"crossref","unstructured":"Painter, M., Lacerda, B., Hawes, N.: Convex hull Monte-Carlo tree-search. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 30, pp. 217\u2013225 (2020)","DOI":"10.1609\/icaps.v30i1.6664"},{"key":"58_CR24","unstructured":"Pezzato, C., Hernandez, C., Wisse, M.: Active inference and behavior trees for reactive action planning and execution in robotics. arXiv preprint arXiv:2011.09756 (2020)"},{"key":"58_CR25","unstructured":"Silver, D., et al.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815 (2017)"},{"key":"58_CR26","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)"},{"key":"58_CR27","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"key":"58_CR28","unstructured":"Thomas, P.S., Brunskill, E.: Policy gradient methods for reinforcement learning with function approximation and action-dependent baselines. arXiv preprint arXiv:1706.06643 (2017)"},{"key":"58_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103629","volume":"133","author":"M Tomy","year":"2020","unstructured":"Tomy, M., Lacerda, B., Hawes, N., Wyatt, J.L.: Battery charge scheduling in long-life autonomous mobile robots via multi-objective decision making under uncertainty. Robot. Auton. Syst. 133, 103629 (2020)","journal-title":"Robot. Auton. Syst."},{"key":"58_CR30","unstructured":"Toussaint, M., Charlin, L., Poupart, P.: Hierarchical pomdp controller optimization by likelihood maximization. In: UAI, vol. 24, pp. 562\u2013570 (2008)"},{"key":"58_CR31","unstructured":"Toussaint, M., Harmeling, S., Storkey, A.: Probabilistic inference for solving (po) mdps. University of Edinburgh, School of Informatics Research Report EDI-INF-RR-0934 (2006)"},{"key":"58_CR32","doi-asserted-by":"crossref","unstructured":"Toussaint, M., Storkey, A.: Probabilistic inference for solving discrete and continuous state markov decision processes. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 945\u2013952. ACM (2006)","DOI":"10.1145\/1143844.1143963"},{"key":"58_CR33","unstructured":"Verma, D., Rao, R.P.: Goal-based imitation as probabilistic inference over graphical models. In: Advances in Neural Information Processing Systems, pp. 1393\u20131400 (2006)"},{"key":"58_CR34","unstructured":"Yoon, S.W., Fern, A., Givan, R.: Ff-replan: a baseline for probabilistic planning. In: ICAPS, vol. 7, pp. 352\u2013359 (2007)"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-93736-2_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T21:02:09Z","timestamp":1726693329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-93736-2_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030937355","9783030937362"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-93736-2_58","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"869","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"210","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}