{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:58:38Z","timestamp":1779901118418,"version":"3.53.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031442223","type":"print"},{"value":"9783031442230","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44223-0_6","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"63-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Latent-Conditioned Policy Gradient for\u00a0Multi-Objective Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Takuya","family":"Kanazawa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chetan","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"6_CR1","unstructured":"Abels, A., Roijers, D.M., Lenaerts, T., Now\u00e9, A., Steckelmacher, D.: Dynamic weights in multi-objective deep reinforcement learning. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, pp. 9\u201315 June 2019, California, USA (2019)"},{"key":"6_CR2","unstructured":"Basaklar, T., Gumussoy, S., Ogras, \u00dc.Y.: PD-MORL: preference-driven multi-objective reinforcement learning algorithm. CoRR abs\/2208.07914 (2022)"},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"89497","DOI":"10.1109\/ACCESS.2020.2990567","volume":"8","author":"J Blank","year":"2020","unstructured":"Blank, J., Deb, K.: Pymoo: multi-objective optimization in python. IEEE Access 8, 89497\u201389509 (2020)","journal-title":"IEEE Access"},{"key":"6_CR4","unstructured":"Bouchacourt, D., Mudigonda, P.K., Nowozin, S.: DISCO Nets : dissimilarity coefficients networks. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Annual Conference on Neural Information Processing Systems 2016, December 5\u201310, 2016, Barcelona, Spain (2016)"},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1002\/wrcr.20295","volume":"49","author":"A Castelletti","year":"2013","unstructured":"Castelletti, A., Pianosi, F., Restelli, M.: A multiobjective reinforcement learning approach to water resourcessystems operation: pareto frontier approximation in a single run. Water Resour. Res. 49, 3476\u20133486 (2013)","journal-title":"Water Resour. Res."},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Castelletti, A., Pianosi, F., Restelli, M.: Tree-based fitted q-iteration for multi-objective markov decision problems. In: Editors (ed.) The 2012 International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia, June 10\u201315, 2012. pp. 1\u20138. IEEE (2012)","DOI":"10.1109\/IJCNN.2012.6252759"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Ghadirzadeh, A., Bj\u00f6rkman, M., Jensfelt, P.: Meta-learning for multi-objective reinforcement learning. In: Editors (ed.) 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 977\u2013983 (2019)","DOI":"10.1109\/IROS40897.2019.8968092"},{"key":"6_CR8","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, July 10\u201315, 2018 (2018)"},{"key":"6_CR9","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/BF01197559","volume":"14","author":"I Das","year":"1997","unstructured":"Das, I., Dennis, J.E.: A closer look at drawbacks of minimizing weighted sums of objectives for Pareto set generation in multicriteria optimization problems. Struct. Optim. 14, 63\u201369 (1997)","journal-title":"Struct. Optim."},{"key":"6_CR10","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., Levine, S.: diversity is all you need: learning skills without a reward function. In: Editors (ed.) 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net (2019)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Hayes, C.F., et al.: A practical guide to multi-objective reinforcement learning and planning. Auton. Agents Multi Agent Syst. 36(1), 26 (2022)","DOI":"10.1007\/s10458-022-09552-y"},{"key":"6_CR12","unstructured":"Kanazawa, T.: (2023), www.github.com\/TaTKSM\/LCMOPG"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Kanazawa, T., Gupta, C.: Sample-based uncertainty quantification with a single deterministic neural network. In: B\u00e4ck, T., van Stein, B., Wagner, C., Garibaldi, J.M., Lam, H.K., Cottrell, M., Doctor, F., Filipe, J., Warwick, K., Kacprzyk, J. (eds.) Proceedings of the 14th International Joint Conference on Computational Intelligence, IJCCI 2022, Valletta, Malta, October 24\u201326, 2022. pp. 292\u2013304. SCITEPRESS (2022)","DOI":"10.5220\/0011546800003332"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Kanazawa, T., Gupta, C.: Latent-conditioned policy gradient for multi-objective deep reinforcement learning. CoRR abs\/2303.08909 (2023)","DOI":"10.1007\/978-3-031-44223-0_6"},{"issue":"3","key":"6_CR15","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1109\/TSMC.2014.2358639","volume":"45","author":"C Liu","year":"2015","unstructured":"Liu, C., Xu, X., Hu, D.: Multiobjective reinforcement learning: a comprehensive overview. IEEE Trans. Syst. Man Cybern. Syst. 45(3), 385\u2013398 (2015)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"7540","key":"6_CR16","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"1","key":"6_CR17","first-page":"3483","volume":"15","author":"KV Moffaert","year":"2014","unstructured":"Moffaert, K.V., Now\u00e9, A.: Multi-objective reinforcement learning using sets of pareto dominating policies. J. Mach. Learn. Res. 15(1), 3483\u20133512 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR18","unstructured":"Mossalam, H., Assael, Y.M., Roijers, D.M., Whiteson, S.: Multi-objective deep reinforcement learning. In: NIPS 2016 Workshop on Deep Reinforcement Learning, CoRR abs\/1610.02707 (2016)"},{"key":"6_CR19","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neucom.2016.11.094","volume":"263","author":"S Parisi","year":"2017","unstructured":"Parisi, S., Pirotta, M., Peters, J.: Manifold-based multi-objective policy search with sample reuse. Neurocomputing 263, 3\u201314 (2017)","journal-title":"Neurocomputing"},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1613\/jair.4961","volume":"57","author":"S Parisi","year":"2016","unstructured":"Parisi, S., Pirotta, M., Restelli, M.: Multi-objective Reinforcement Learning through continuous pareto manifold approximation. J. Artif. Intell. Res. 57, 187\u2013227 (2016)","journal-title":"J. Artif. Intell. Res."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Parisi, S., Pirotta, M., Smacchia, N., Bascetta, L., Restelli, M.: Policy gradient approaches for multi-objective sequential decision making. In: Editors (ed.) 2014 International Joint Conference on Neural Networks, IJCNN 2014, Beijing, China, July 6\u201311, 2014. pp. 2323\u20132330. IEEE (2014)","DOI":"10.1109\/IJCNN.2014.6889738"},{"key":"6_CR22","unstructured":"Pirotta, M., Parisi, S., Restelli, M.: Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation. In: Bonet, B., Koenig, S. (eds.) Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25\u201330, 2015, Austin, Texas, USA. pp. 2928\u20132934. AAAI Press (2015)"},{"key":"6_CR23","unstructured":"Reymond, M.: (2022), www.github.com\/mathieu-reymond\/pareto-conditioned-networks\/tree\/main\/envs\/minecart"},{"key":"6_CR24","unstructured":"Reymond, M., Bargiacchi, E., Now\u00e9, A.: Pareto Conditioned Networks. In: Faliszewski, P., Mascardi, V., Pelachaud, C., Taylor, M.E. (eds.) 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022, Auckland, New Zealand, May 9\u201313, 2022. pp. 1110\u20131118 (2022)"},{"key":"6_CR25","unstructured":"Reymond, M., Nowe, A.: Pareto-DQN: approximating the Pareto front in complex multi-objective decision problems. In: Editors (ed.) Proceedings of the Adaptive and Learning Agents Workshop 2019 (ALA-19) at AAMAS (2019)"},{"key":"6_CR26","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1613\/jair.3987","volume":"48","author":"DM Roijers","year":"2013","unstructured":"Roijers, D.M., Vamplew, P., Whiteson, S., Dazeley, R.: A survey of multi-objective sequential decision-making. J. Artif. Intell. Res. 48, 67\u2013113 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"6_CR27","unstructured":"Schmidhuber, J.: Reinforcement learning upside down: don\u2019t predict rewards - just map them to actions. CoRR abs\/1912.02875 (2019)"},{"key":"6_CR28","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press, second edn. (2018)"},{"issue":"1\u20132","key":"6_CR29","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10994-010-5232-5","volume":"84","author":"P Vamplew","year":"2011","unstructured":"Vamplew, P., Dazeley, R., Berry, A., Issabekov, R., Dekker, E.: Empirical evaluation methods for multiobjective reinforcement learning algorithms. Mach. Learn. 84(1\u20132), 51\u201380 (2011)","journal-title":"Mach. Learn."},{"key":"6_CR30","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-540-89378-3_37","volume-title":"AI 2008: Advances in Artificial Intelligence","author":"P Vamplew","year":"2008","unstructured":"Vamplew, P., Yearwood, J., Dazeley, R., Berry, A.: On the Limitations of Scalarisation for Multi-objective Reinforcement Learning of Pareto Fronts. In: Wobcke, W., Zhang, M. (eds.) AI 2008: Advances in Artificial Intelligence, pp. 372\u2013378. Springer, Berlin Heidelberg, Berlin, Heidelberg (2008)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Van Moffaert, K., Drugan, M.M., Now\u00e9, A.: Scalarized multi-objective reinforcement learning: Novel design techniques. In: Editors (ed.) 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL). pp. 191\u2013199 (2013)","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"6_CR33","unstructured":"Xu, J., Tian, Y., Ma, P., Rus, D., Sueda, S., Matusik, W.: Prediction-guided multi-objective reinforcement learning for continuous robot control. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, pp. 13\u201318 July 2020 (2020)"},{"key":"6_CR34","unstructured":"Yang, R.: (2019), www.github.com\/RunzheYang\/MORL\/blob\/master\/synthetic\/envs\/fruit_tree.py"},{"key":"6_CR35","unstructured":"Yang, R., Sun, X., Narasimhan, K.: A Generalized algorithm for multi-objective reinforcement learning and policy adaptation. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada (2019)"},{"issue":"4","key":"6_CR36","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/4235.797969","volume":"3","author":"E Zitzler","year":"1999","unstructured":"Zitzler, E., Thiele, L.: Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Trans. Evol. Comput. 3(4), 257\u2013271 (1999)","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"2","key":"6_CR37","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TEVC.2003.810758","volume":"7","author":"E Zitzler","year":"2003","unstructured":"Zitzler, E., Thiele, L., Laumanns, M., Fonseca, C.M., da Fonseca, V.G.: Performance assessment of multiobjective optimizers: an analysis and review. IEEE Trans. Evol. Comput. 7(2), 117\u2013132 (2003)","journal-title":"IEEE Trans. Evol. Comput."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44223-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T06:41:58Z","timestamp":1703227318000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44223-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442223","9783031442230"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44223-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted : 9 Abstract","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)"}}]}}