{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T05:20:55Z","timestamp":1754112055275,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031539657"},{"type":"electronic","value":"9783031539664"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-53966-4_19","type":"book-chapter","created":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T18:02:29Z","timestamp":1707933749000},"page":"255-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Solving Mixed Influence Diagrams by\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"S. D.","family":"Prestwich","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,15]]},"reference":[{"key":"19_CR1","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s10107-003-0475-6","volume":"100","author":"S Ahmed","year":"2004","unstructured":"Ahmed, S., Tawarmalani, M., Sahinidis, N.V.: A finite branch-and-bound algorithm for two-stage stochastic integer programs. Math. Program. 100, 355\u2013377 (2004)","journal-title":"Math. Program."},{"issue":"3","key":"19_CR2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1504\/IJCSM.2010.037445","volume":"3","author":"R Arora","year":"2010","unstructured":"Arora, R., Arora, S.R.: An algorithm for non-linear multi-level integer programming problems. Int. J. Comput. Sci. Math. 3(3), 211\u2013225 (2010)","journal-title":"Int. J. Comput. Sci. Math."},{"key":"19_CR3","doi-asserted-by":"publisher","unstructured":"Birge, J.R., Louveaux, F.V.: Introduction to Stochastic Programming. Springer, New York (2011). https:\/\/doi.org\/10.1007\/978-1-4614-0237-4","DOI":"10.1007\/978-1-4614-0237-4"},{"key":"19_CR4","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.ijar.2005.10.009","volume":"42","author":"A Cano","year":"2006","unstructured":"Cano, A., G\u00f3mez, M., Moral, S.: A forward-backward Monte Carlo method for solving influence diagrams. Int. J. Approx. Reason. 42, 119\u2013135 (2006)","journal-title":"Int. J. Approx. Reason."},{"issue":"1","key":"19_CR5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1287\/mnsc.6.1.73","volume":"6","author":"A Charnes","year":"1959","unstructured":"Charnes, A., Cooper, W.W.: Chance-constrained programming. Manag. Sci. 6(1), 73\u201379 (1959)","journal-title":"Manag. Sci."},{"issue":"3","key":"19_CR6","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1287\/mnsc.1030.0138","volume":"50","author":"JM Charnes","year":"2004","unstructured":"Charnes, J.M., Shenoy, P.P.: Multistage Monte Carlo method for solving influence diagrams using local computation. Manag. Sci. 50(3), 405\u2013418 (2004)","journal-title":"Manag. Sci."},{"key":"19_CR7","unstructured":"Dechter, R.: A new perspective on algorithms for optimizing policies under uncertainty. In: Artificial Intelligence Planning Systems, pp. 72\u201381 (2000)"},{"issue":"3","key":"19_CR8","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSMCA.2003.822967","volume":"34","author":"M Diehl","year":"2004","unstructured":"Diehl, M., Haimes, Y.: Influence diagrams with multiple objectives and tradeoff analysis. IEEE Trans. Syst. Man Cybern. Part A 34(3), 293\u2013304 (2004)","journal-title":"IEEE Trans. Syst. Man Cybern. Part A"},{"issue":"2","key":"19_CR9","doi-asserted-by":"publisher","first-page":"154","DOI":"10.3923\/tasr.2008.154.164","volume":"3","author":"MMK Elshafei","year":"2008","unstructured":"Elshafei, M.M.K., El-Sherberry, M.S.: Interactive Bi-level multiobjective stochastic integer linear programming problem. Trends Appl. Sci. Res. 3(2), 154\u2013164 (2008)","journal-title":"Trends Appl. Sci. Res."},{"key":"19_CR10","unstructured":"Everitt, T., Kumar, R., Krakovna, V., Legg, S.: Modeling AGI safety frameworks with causal influence diagrams. In: Proceedings of the Workshop on Artificial Intelligence Safety, CEUR Workshop, vol. 2419 (2019)"},{"key":"19_CR11","unstructured":"G\u00e1bor, Z., Kalm\u00e1r, Z., Szepesv\u00e1ri, C.: Multi-criteria reinforcement learning. In: Proceedings of the 15th International Conference on Machine Learning, pp. 197\u2013205 (1998)"},{"key":"19_CR12","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1613\/jair.2503","volume":"33","author":"Y Gal","year":"2008","unstructured":"Gal, Y., Pfeffer, A.: Networks of influence diagrams: a formalism for representing agents\u2019 beliefs and decision-making processes. J. Artif. Intell. Res. 33, 109\u2013147 (2008)","journal-title":"J. Artif. Intell. Res."},{"key":"19_CR13","first-page":"1437","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16, 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"19_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2014.08.071","volume":"293","author":"I Giagkiozis","year":"2015","unstructured":"Giagkiozis, I., Fleming, P.J.: Methods for multi-objective optimization: an analysis. Inf. Sci. 293, 1\u201316 (2015)","journal-title":"Inf. Sci."},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Polich, K., Gmytrasiewicz, G.: Interactive dynamic influence diagrams. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, Communications in Computer and Information Science, vol. 288, pp. 623\u2013630 (2007)","DOI":"10.1145\/1329125.1329166"},{"issue":"3","key":"19_CR16","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1016\/j.ejor.2018.09.015","volume":"273","author":"J Gonz\u00e1lez-Ortega","year":"2019","unstructured":"Gonz\u00e1lez-Ortega, J., Insua, D.R., Cano, J.: Adversarial risk analysis for bi-agent influence diagrams: an algorithmic approach. Eur. J. Oper. Res. 273(3), 1085\u20131096 (2019)","journal-title":"Eur. J. Oper. Res."},{"key":"19_CR17","unstructured":"Gu, S., et al.: A Review of Safe Reinforcement Learning: Methods, Theory and Applications. CoRR abs\/2205.10330 (2022)"},{"key":"19_CR18","unstructured":"Howard, R.A., Matheson, J.E.: Influence Diagrams. Readings in Decision Analysis, Strategic Decisions Group, Menlo Park, CA, chapter 38, pp. 763\u2013771 (1981)"},{"key":"19_CR19","unstructured":"Huang, S.H., et al.: A constrained multi-objective reinforcement learning framework. In: CoRL, pp. 883\u2013893 (2021)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Hyatt, R.M., Cozzie, A.: The effect of hash signature collisions in a chess program. ICGA J. 28(3), 131\u2013139 (2005)","DOI":"10.3233\/ICG-2005-28302"},{"key":"19_CR21","unstructured":"Jenzarli, A.: Information\/relevance influence diagrams. In: Proceedings of the 11th conference on Uncertainty in Artificial Intelligence (UAI), Quebec, Canada, pp. 329\u2013337 (1995)"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Jensen, F., Jensen, V., Dittmer, S.: From influence diagrams to junction trees. In: Uncertainty in Artificial Intelligence, pp. 367\u2013363 (1994)","DOI":"10.1016\/B978-1-55860-332-5.50051-1"},{"issue":"1","key":"19_CR23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0899-8256(02)00544-4","volume":"45","author":"D Koller","year":"2001","unstructured":"Koller, D., Milch, B.: Multi-agent influence diagrams for representing and solving games. Games Econ. Behav. 45(1), 181\u2013221 (2001)","journal-title":"Games Econ. Behav."},{"key":"19_CR24","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1016\/j.ijar.2016.11.018","volume":"88","author":"V Kratochv\u00edl","year":"2017","unstructured":"Kratochv\u00edl, V., Vomlel, J.: Influence diagrams for speed profile optimization. Int. J. Approx. Reason. 88, 567\u2013586 (2017)","journal-title":"Int. J. Approx. Reason."},{"key":"19_CR25","first-page":"1238","volume":"47","author":"SL Lauritzen","year":"2001","unstructured":"Lauritzen, S.L., Nilsson, D.: Representing and solving decision problems with limited information. Manag. Sci. 47, 1238\u20131251 (2001)","journal-title":"Manag. Sci."},{"key":"19_CR26","unstructured":"Lee, J., Marinescu, R., Ihler, A., Dechter, R.: A weighted mini-bucket bound for solving influence diagrams. In: Proceedings of the Conference on Uncertainty in Artificial Intelligence (2019)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Marinescu, R., Lee, J., Dechter, R.: A new bounding scheme for influence diagrams. In: Proceedings of the 35th Conference on Artificial Intelligence, pp. 12158\u201312165 (2021)","DOI":"10.1609\/aaai.v35i13.17443"},{"key":"19_CR28","unstructured":"Marinescu, R., Razak, A., Wilson, N.: Multi-objective influence diagrams. In: Proceedings of the Conference on Uncertainty in Artificial Intelligence (2012)"},{"key":"19_CR29","unstructured":"Mishra, S., Verma, A.B.: A non-differential approach for solving tri-level programming problems. Am. Int. J. Res. Sci. Technol. Eng. Math. (2015)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"van Moffaert, K., Drugan, M.M., Now\u00e9, A.: Scalarized multi-objective reinforcement learning: novel design techniques. In: Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pp. 191\u2013199. IEEE (2013)","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Powell, W.B.: Reinforcement Learning and Stochastic Optimization: A Unified Framework for Sequential Decisions. Wiley, Hoboken (2022)","DOI":"10.1002\/9781119815068"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Prestwich, S.D., Toffano, F., Wilson, N.: A probabilistic programming language for influence diagrams. In: Proceedings of the 11th International Conference on Scalable Uncertainty Management (2017)","DOI":"10.1007\/978-3-319-67582-4_18"},{"issue":"6","key":"19_CR33","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1287\/opre.34.6.871","volume":"34","author":"RD Shachter","year":"1986","unstructured":"Shachter, R.D.: Evaluating influence diagrams. Oper. Res. 34(6), 871\u2013882 (1986)","journal-title":"Oper. Res."},{"issue":"1","key":"19_CR34","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1287\/opre.40.3.463","volume":"40","author":"P Shenoy","year":"1992","unstructured":"Shenoy, P.: Valuation-based systems for Bayesian decision analysis. Oper. Res. 40(1), 463\u2013484 (1992)","journal-title":"Oper. Res."},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Skalse, J., Hammond, L., Griffin, C., Abate, A.: Lexicographic multi-objective reinforcement learning. In: Proceedings of the 31st International Joint Conference on Artificial Intelligence, pp. 3430\u20133436 (2022)","DOI":"10.24963\/ijcai.2022\/476"},{"key":"19_CR36","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Dynamic programming and influence diagrams. IEEE Trans. Syst. Man Cybern. 20(1), 365\u2013379 (1990)","DOI":"10.1109\/21.52548"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Watthayu, W.: Representing and solving influence diagram in multi-criteria decision making: a loopy belief propagation method. In: Proceedings of the International Symposium on Computer Science and Its Applications, pp. 118\u2013125 (2008)","DOI":"10.1109\/CSA.2008.76"},{"key":"19_CR39","unstructured":"Yuan, C., Wu, X.: Solving influence diagrams using heuristic search. In: Proceedings of the International Symposium on Artificial Intelligence and Mathematics (2010)"},{"issue":"4","key":"19_CR40","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1111\/j.1468-0394.2012.00639.x","volume":"30","author":"LH Zhou","year":"2013","unstructured":"Zhou, L.H., Kevin, L., Liu, W.Y.: Game theory-based influence diagrams. Expert Syst. 30(4), 341\u2013351 (2013)","journal-title":"Expert Syst."},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Zobrist, A.L.: A new hashing method with application for game playing. Technical report 88, Computer Sciences Department, University of Wisconsin, Madison, Wisconsin (1969). Also: International Computer Chess Association Journal 13(2), 69\u201373, 1990","DOI":"10.3233\/ICG-1990-13203"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53966-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T18:05:06Z","timestamp":1707933906000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53966-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031539657","9783031539664"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53966-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2023.icas.cc\/","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":"In-house system and EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"119","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":"72","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":"61% - 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":"5-6","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":"1-2","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)"}}]}}