{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:45:21Z","timestamp":1743039921797,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031216886"},{"type":"electronic","value":"9783031216893"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-21689-3_3","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"30-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploration Versus Exploitation in\u00a0Model-Based Reinforcement Learning: An Empirical Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0586-5412","authenticated-orcid":false,"given":"\u00c2ngelo Greg\u00f3rio","family":"Lovatto","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9128-0188","authenticated-orcid":false,"given":"Leliane Nunes","family":"de Barros","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2297-6349","authenticated-orcid":false,"given":"Denis D.","family":"Mau\u00e1","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"3_CR1","unstructured":"Amos, B., Stanton, S., Yarats, D., Wilson, A.G.: On the model-based stochastic value gradient for continuous reinforcement learning. CoRR abs\/2008.1 (2020)"},{"key":"3_CR2","unstructured":"Chan, S.C.Y., Fishman, S., Korattikara, A., Canny, J., Guadarrama, S.: Measuring the reliability of reinforcement learning algorithms. In: ICLR (2020)"},{"issue":"353","key":"3_CR3","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/01621459.1976.10481508","volume":"71","author":"A Charnes","year":"1976","unstructured":"Charnes, A., Frome, E.L., Yu, P.L.: The equivalence of generalized least squares and maximum likelihood estimates in the exponential family. J. Am. Stat. Assoc. 71(353), 169\u2013171 (1976)","journal-title":"J. Am. Stat. Assoc."},{"key":"3_CR4","unstructured":"Clavera, I., Fu, Y., Abbeel, P.: Model-augmented actor-critic: backpropagating through paths. In: ICLR (2020)"},{"key":"3_CR5","unstructured":"D\u2019Oro, P., Jaskowski, W.: How to learn a useful critic? Model-based Action-Gradient-Estimator Policy Optimization. In: NeurIPS (2020)"},{"key":"3_CR6","unstructured":"Engstrom, L., et al.: Implementation matters in deep RL: a case study on PPO and TRPO. In: ICLR (2020)"},{"issue":"3\u20134","key":"3_CR7","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Fran\u00e7ois-Lavet","year":"2018","unstructured":"Fran\u00e7ois-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J.: An introduction to deep reinforcement learning. Found. Trends Mach. Learn. 11(3\u20134), 219\u2013354 (2018)","journal-title":"Found. Trends Mach. Learn."},{"key":"3_CR8","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: ICML. Proceedings of Machine Learning Research, vol. 80, pp. 1582\u20131591. PMLR (2018)"},{"key":"3_CR9","unstructured":"Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: AAAI, pp. 3207\u20133214 (2018)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"3_CR11","unstructured":"Ilyas, A., et al.: A closer look at deep policy gradients. In: ICLR (2020)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Islam, R., Henderson, P., Gomrokchi, M., Precup, D.: Reproducibility of benchmarked deep reinforcement learning tasks for continuous control. CoRR (2017)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"3_CR13","unstructured":"Liu, Z., Li, X., Kang, B., Darrell, T.: Regularization matters for policy optimization - an empirical study on continuous control. In: International Conference on Learning Representations (2021)"},{"key":"3_CR14","unstructured":"Lovatto, A.G., Bueno, T.P., Mau\u00e1, D.D., de Barros, L.N.: Decision-aware model learning for actor-critic methods: when theory does not meet practice. In: Proceedings on \u201cI Can\u2019t Believe It\u2019s Not Better!\u201d at NeurIPS Workshops. Proceedings of Machine Learning Research, vol. 137, pp. 76\u201386 (2020)"},{"key":"3_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-030-91702-9_3","volume-title":"Intelligent Systems","author":"\u00c2G Lovatto","year":"2021","unstructured":"Lovatto, \u00c2.G., Bueno, T.P., de Barros, L.N.: Gradient estimation in model-based reinforcement learning: a study on linear quadratic environments. In: Britto, A., Valdivia Delgado, K. (eds.) BRACIS 2021. LNCS (LNAI), vol. 13073, pp. 33\u201347. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-91702-9_3"},{"issue":"7540","key":"3_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."},{"key":"3_CR17","unstructured":"Moerland, T.M., Broekens, J., Jonker, C.M.: Model-based reinforcement learning: a survey. In: Proceedings of the International Conference on Electronic Business 2018-December, pp. 421\u2013429 (2020)"},{"issue":"2","key":"3_CR18","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s10846-017-0468-y","volume":"86","author":"AS Polydoros","year":"2017","unstructured":"Polydoros, A.S., Nalpantidis, L.: Survey of model-based reinforcement learning: applications on robotics. J. Intell. Robot. Syst. 86(2), 153\u2013173 (2017). https:\/\/doi.org\/10.1007\/s10846-017-0468-y","journal-title":"J. Intell. Robot. Syst."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Recht, B.: A Tour of Reinforcement Learning: the view from continuous control. Ann. Rev. Control Robot. Auton. Syst. 2(1), 253\u2013279 (2019)","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"3_CR20","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms. CoRR abs\/1609.04747 (2016)"},{"key":"3_CR21","unstructured":"Schulman, J., Heess, N., Weber, T., Abbeel, P.: Gradient estimation using stochastic computation graphs. In: NIPS, pp. 3528\u20133536 (2015)"},{"key":"3_CR22","unstructured":"Silver, D., Lever, G.: Deterministic policy gradient. In: Proceedings of the 31st International Conference on Machine Learning, vol. 32(1), pp. 387\u2013395, January 2014"},{"key":"3_CR23","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2018)","edition":"2"},{"key":"3_CR24","first-page":"1","volume":"4","author":"C Szepesv\u00e1ri","year":"2010","unstructured":"Szepesv\u00e1ri, C.: Algorithms for reinforcement learning. Synth. Lect. Artif. Intell. Mach. Learn. 4, 1\u20133 (2010)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"issue":"10","key":"3_CR25","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1109\/9.539425","volume":"41","author":"AL Tits","year":"1996","unstructured":"Tits, A.L., Yang, Y.: Globally convergent algorithms for robust pole assignment by state feedback. IEEE Trans. Autom. Control 41(10), 1432\u20131452 (1996)","journal-title":"IEEE Trans. Autom. Control"},{"key":"3_CR26","doi-asserted-by":"crossref","first-page":"269","DOI":"10.7551\/mitpress\/1535.003.0018","volume-title":"Optimal Control Theory. Bayesian Brain: Probabilistic Approaches to Neural Coding","author":"E Todorov","year":"2006","unstructured":"Todorov, E.: Optimal Control Theory. Bayesian Brain: Probabilistic Approaches to Neural Coding, pp. 269\u2013298. MIT Press, Cambridge (2006)"},{"key":"3_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8086-2","volume-title":"Optimal Control","author":"RB Vinter","year":"2010","unstructured":"Vinter, R.B., Vinter, R.: Optimal Control. Springer, Boston (2010). https:\/\/doi.org\/10.1007\/978-0-8176-8086-2"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21689-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T10:41:05Z","timestamp":1701427265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Campinas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","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":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www2.sbc.org.br\/bracis2022\/","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":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"225","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":"89","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":"40% - 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","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)"}}]}}