{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:16:33Z","timestamp":1743088593833,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031216855"},{"type":"electronic","value":"9783031216862"}],"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\/978-3-031-21686-2_16","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T08:30:15Z","timestamp":1668760215000},"page":"221-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving the\u00a0FQF Distributional Reinforcement Learning Algorithm in\u00a0MinAtar Environment"],"prefix":"10.1007","author":[{"given":"J\u00falio C\u00e9sar Mendes de","family":"Resende","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edimilson Batista dos","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos Antonio de Matos","family":"Laia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"16_CR1","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 449\u2013458. PMLR, 06\u201311 August 2017. http:\/\/proceedings.mlr.press\/v70\/bellemare17a.html"},{"issue":"1","key":"16_CR2","first-page":"253","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Int. Res. 47(1), 253\u2013279 (2013)","journal-title":"J. Artif. Int. Res."},{"key":"16_CR3","unstructured":"Ceron, J.S.O., Castro, P.S.: Revisiting rainbow: promoting more insightful and inclusive deep reinforcement learning research. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 1373\u20131383. PMLR, 18\u201324 July 2021. http:\/\/proceedings.mlr.press\/v139\/ceron21a.html"},{"key":"16_CR4","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1096\u20131105. PMLR, 10\u201315 July 2018. http:\/\/proceedings.mlr.press\/v80\/dabney18a.html"},{"key":"16_CR5","unstructured":"Dabney, W., Rowland, M., Bellemare, M.G., Munos, R.: Distributional reinforcement learning with quantile regression. In: McIlraith, S.A., Weinberger, K.Q. (eds.) Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), The 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2\u20137 February 2018, pp. 2892\u20132901. AAAI Press (2018)"},{"key":"16_CR6","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. In: International Conference on Learning Representations (2018). http:\/\/openreview.net\/forum?id=rywHCPkAW"},{"key":"16_CR7","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1861\u20131870. PMLR, 10\u201315 July 2018. http:\/\/proceedings.mlr.press\/v80\/haarnoja18b.html"},{"key":"16_CR8","unstructured":"Hasselt, H.v., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 2094\u20132100. AAAI 2016, AAAI Press (2016)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. AAAI 2018\/IAAI 2018\/EAAI 2018, AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"issue":"1","key":"16_CR10","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","volume":"35","author":"PJ Huber","year":"1964","unstructured":"Huber, P.J.: Robust estimation of a location parameter. Ann. Math. Stat. 35(1), 73\u2013101 (1964). https:\/\/doi.org\/10.1214\/aoms\/1177703732","journal-title":"Ann. Math. Stat."},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Kendall, A., et al.: Learning to drive in a day, pp. 8248\u20138254 (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8793742","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"16_CR12","volume-title":"Machine Learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell, T.M.: Machine Learning. McGraw-Hill, New York (1997)"},{"key":"16_CR13","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning (2015). https:\/\/doi.org\/10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"16_CR14","unstructured":"Rummery, G., Niranjan, M.: On-Line Q-learning Using Connectionist Systems. Technical report. CUED\/F-INFENG\/TR 166, Cambridge University, Cambridge (1994)"},{"key":"16_CR15","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay (2016). http:\/\/arxiv.org\/abs\/1511.05952. published as a conference paper at ICLR 2016"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Schoettler, G., et al.: Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5548\u20135555 (2020)","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Subramanian, A., Chitlangia, S., Baths, V.: Reinforcement learning and its connections with neuroscience and psychology. Neural Netw. 145(C), 271\u2013287 (2022). https:\/\/doi.org\/10.1016\/j.neunet.2021.10.003","DOI":"10.1016\/j.neunet.2021.10.003"},{"key":"16_CR18","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge second edn. (2018). http:\/\/incompleteideas.net\/book\/the-book-2nd.html"},{"key":"16_CR19","unstructured":"Vieillard, N., Pietquin, O., Geist, M.: Munchausen reinforcement learning. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol. 33, pp. 4235\u20134246. Curran Associates, Inc. (2020)"},{"key":"16_CR20","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1995\u20132003. PMLR, New York, 20\u201322 Jun 2016. http:\/\/proceedings.mlr.press\/v48\/wangf16.html"},{"key":"16_CR21","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, King\u2019s College, Oxford (1989)"},{"key":"16_CR22","unstructured":"Yang, D., Zhao, L., Lin, Z., Qin, T., Bian, J., Liu, T.Y.: Fully parameterized quantile function for distributional reinforcement learning. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"16_CR23","unstructured":"Young, K., Tian, T.: MinAtar: an atari-inspired testbed for thorough and reproducible reinforcement learning experiments. arXiv preprint arXiv:1903.03176 (2019). http:\/\/arxiv.org\/abs\/1903.03176"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21686-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:10:53Z","timestamp":1709831453000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21686-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216855","9783031216862"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21686-2_16","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)"}}]}}