{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:15:40Z","timestamp":1743041740353,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030917012"},{"type":"electronic","value":"9783030917029"}],"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\/978-3-030-91702-9_3","type":"book-chapter","created":{"date-parts":[[2021,11,27]],"date-time":"2021-11-27T20:02:46Z","timestamp":1638043366000},"page":"33-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Gradient Estimation in Model-Based Reinforcement Learning: A Study on Linear Quadratic Environments"],"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\/0000-0003-1999-9697","authenticated-orcid":false,"given":"Thiago Pereira","family":"Bueno","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9128-0188","authenticated-orcid":false,"given":"Leliane Nunes","family":"de Barros","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,28]]},"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 arXiv:2008.1 (2020)"},{"key":"3_CR2","unstructured":"Byravan, A., et al.: Imagined value gradients: model-based policy optimization with transferable latent dynamics models. In: CoRL. Proceedings of Machine Learning Research, vol. 100, pp. 566\u2013589. PMLR (2019)"},{"key":"3_CR3","unstructured":"Chan, S.C.Y., Fishman, S., Korattikara, A., Canny, J., Guadarrama, S.: Measuring the reliability of reinforcement learning algorithms. In: ICLR. OpenReview.net (2020)"},{"key":"3_CR4","unstructured":"Clavera, I., Fu, Y., Abbeel, P.: Model-augmented actor-critic: backpropagating through paths. In: ICLR. OpenReview.net (2020). https:\/\/openreview.net\/forum?id=Skln2A4YDB"},{"key":"3_CR5","unstructured":"Deisenroth, M.P., Rasmussen, C.E.: PILCO: a model-based and data-efficient approach to policy search. In: Getoor, L., Scheffer, T. (eds.) Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, 28 June\u20132 July 2011, pp. 465\u2013472. Omnipress (2011). https:\/\/icml.cc\/2011\/papers\/323_icmlpaper.pdf"},{"key":"3_CR6","unstructured":"Engstrom, L., et al.: Implementation matters in deep RL: a case study on PPO and TRPO. In: ICLR. OpenReview.net (2020). https:\/\/github.com\/implementation-matters\/code-for-paper"},{"key":"3_CR7","volume-title":"Deep Learning. Adaptive Computation and Machine Learning","author":"IJ Goodfellow","year":"2016","unstructured":"Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)"},{"key":"3_CR8","unstructured":"Hafner, D., Lillicrap, T.P., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. In: ICLR. OpenReview.net (2020)"},{"key":"3_CR9","unstructured":"Heess, N., Wayne, G., Silver, D., Lillicrap, T.P., Erez, T., Tassa, Y.: Learning continuous control policies by stochastic value gradients. In: NIPS, pp. 2944\u20132952 (2015). http:\/\/papers.nips.cc\/paper\/5796-learning-continuous-control-policies-by-stochastic-value-gradients"},{"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. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"3_CR11","unstructured":"Ilyas, A., et al.: A closer look at deep policy gradients. In: ICLR. OpenReview.net (2020)"},{"key":"3_CR12","unstructured":"Islam, R., Henderson, P., Gomrokchi, M., Precup, D.: Reproducibility of benchmarked deep reinforcement learning tasks for continuous control. CoRR arXiv:1708.04133 (2017)"},{"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). https:\/\/github.com\/xuanlinli17\/iclr2021_rlreg"},{"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. PMLR, December 2020. http:\/\/proceedings.mlr.press\/v137\/lovatto20a.html"},{"issue":"7540","key":"3_CR15","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_CR16","unstructured":"Moerland, T.M., Broekens, J., Jonker, C.M.: Model-based reinforcement learning: a survey. In: Proceedings of the International Conference on Electronic Business (ICEB) 2018-December, pp. 421\u2013429 (2020). http:\/\/arxiv.org\/abs\/2006.16712"},{"key":"3_CR17","unstructured":"Mohamed, S., Rosca, M., Figurnov, M., Mnih, A.: Monte Carlo gradient estimation in machine learning. J. Mach. Learn. Res. 21, 132:1\u2013132:62 (2020)"},{"key":"3_CR18","unstructured":"Paszke, A., et al.: PyTorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.nips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"3_CR19","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"3_CR20","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_CR21","doi-asserted-by":"publisher","unstructured":"Recht, B.: A tour of reinforcement learning: the view from continuous control. Ann. Rev. Control Robot. Auton. Syst. 2(1), 253\u2013279 (2019). https:\/\/doi.org\/10.1146\/annurev-control-053018-023825, http:\/\/arxiv.org\/abs\/1806.09460","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"3_CR22","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms. CoRR arXiv:1609.04747 (2016)"},{"key":"3_CR23","unstructured":"Schulman, J., Heess, N., Weber, T., Abbeel, P.: Gradient estimation using stochastic computation graphs. In: NIPS, pp. 3528\u20133536 (2015)"},{"key":"3_CR24","unstructured":"Silver, D., Lever, G., Technologies, D., Lever, G.U.Y., Ac, U.C.L.: Deterministic Policy Gradient (DPG). In: Proceedings of the 31st International Conference on Machine Learning, vol. 32, no. 1, pp. 387\u2013395 (2014). http:\/\/proceedings.mlr.press\/v32\/silver14.html"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Szepesv\u00e1ri, C.: Algorithms for Reinforcement Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers (2010). https:\/\/doi.org\/10.2200\/S00268ED1V01Y201005AIM009","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"issue":"10","key":"3_CR26","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). https:\/\/doi.org\/10.1109\/9.539425","journal-title":"IEEE Trans. Autom. Control"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Todorov, E.: Optimal Control Theory. Bayesian Brain: Probabilistic Approaches to Neural Coding, pp. 269\u2013298 (2006)","DOI":"10.7551\/mitpress\/1535.003.0018"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: IEEE International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012). https:\/\/doi.org\/10.1109\/IROS.2012.6386109, http:\/\/ieeexplore.ieee.org\/document\/6386109\/","DOI":"10.1109\/IROS.2012.6386109"},{"key":"3_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Meth. 17, 261\u2013272 (2020). https:\/\/doi.org\/10.1038\/s41592-019-0686-2","journal-title":"Nat. Meth."}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-91702-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:02:19Z","timestamp":1709812939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-91702-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030917012","9783030917029"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-91702-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"28 November 2021","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/c4ai.inova.usp.br\/bracis\/","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":"192","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":"77","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":"3.1","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":"Due to COVID-19, the conference was held as an online event.","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)"}}]}}