{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:42:17Z","timestamp":1743147737340,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031255984"},{"type":"electronic","value":"9783031255991"}],"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\/978-3-031-25599-1_18","type":"book-chapter","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T04:32:27Z","timestamp":1678249947000},"page":"239-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MicroRacer: A Didactic Environment for\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Andrea","family":"Asperti","sequence":"first","affiliation":[]},{"given":"Marco","family":"Del Brutto","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,9]]},"reference":[{"issue":"2","key":"18_CR1","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1109\/TG.2019.2899159","volume":"12","author":"A Asperti","year":"2020","unstructured":"Asperti, A., Cortesi, D., De Pieri, C., Pedrini, G., Sovrano, F.: Crawling in rogue\u2019s dungeons with deep reinforcement techniques. IEEE Trans. Games 12(2), 177\u2013186 (2020)","journal-title":"IEEE Trans. Games"},{"key":"18_CR2","doi-asserted-by":"publisher","unstructured":"Asperti, A., Cortesi, D., Sovrano, F.: Crawling in rogue\u2019s dungeons with (partitioned) A3C. In: Machine Learning, Optimization, and Data Science - 4th International Conference, LOD 2018, Volterra, Italy, 13\u201316 Sep 2018, Revised Selected Papers, vol. 11331 of Lecture Notes in Computer Science, pp. 264\u2013275. Springer (2018). https:\/\/doi.org\/10.1007\/978-3-030-13709-0_22","DOI":"10.1007\/978-3-030-13709-0_22"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Balaji, B., et al. DeepRacer: educational autonomous racing platform for experimentation with sim2real reinforcement learning. arXiv preprint arXiv:abs\/1911.01562 (2019)","DOI":"10.1109\/ICRA40945.2020.9197465"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Behnel, S., Bradshaw, R., Citro, C., Dalcin, L., Seljebotn, D.S., Smith, K.: Cython: the best of both worlds. Comput. Sci. Eng. 13(2), 31\u201339 (2011)","DOI":"10.1109\/MCSE.2010.118"},{"key":"18_CR5","unstructured":"Bellemare, M.G., Dabney, W., Rowland, M.: Distributional Reinforcement Learning. MIT Press, Cambridge (2022). https:\/\/www.distributional-rl.org"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","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. Intell. Res. (JAIR) 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res. (JAIR)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Bisong, E.: Google Colaboratory, pp. 59\u201364. Apress, Berkeley (2019)","DOI":"10.1007\/978-1-4842-4470-8_7"},{"key":"18_CR8","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:abs\/1606.01540 (2016)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Cardamone, L., Loiacono, D., Lanzi, P.L., Bardelli, A.P.: Searching for the optimal racing line using genetic algorithms. In: Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games, pp. 388\u2013394 (2010)","DOI":"10.1109\/ITW.2010.5593330"},{"key":"18_CR10","unstructured":"Chen, B., Francis, J., Oh, J., Nyberg, E., Herbert, S.L.: Safe autonomous racing via approximate reachability on ego-vision (2021)"},{"key":"18_CR11","unstructured":"Brutto, M.D.: MicroRacer: development of a didactic environment for deep reinforcement learning. Master\u2019s thesis, University of Bologna, School of Science, Session III 2021\u201322"},{"key":"18_CR12","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A.M., Koltun, V.: CARLA: an open urban driving simulator. In: 1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, California, USA, 13\u201315 Nov 2017, Proceedings, pp. 1\u201316. PMLR (2017)"},{"key":"18_CR13","unstructured":"Duan, J., Guan, Y., Li, S.E., Ren, Y., Sun, Q., Cheng, B.: Distributional soft actor-critic: off-policy reinforcement learning for addressing value estimation errors. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1\u201315 (2021)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Evans, B., Engelbrecht, H.A., Jordaan, H.W.: Learning the subsystem of local planning for autonomous racing. In: 20th International Conference on Advanced Robotics, ICAR 2021, Ljubljana, Slovenia, Dec 6\u201310 2021, pp. 601\u2013606. IEEE (2021)","DOI":"10.1109\/ICAR53236.2021.9659466"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Evans, B., Engelbrecht, H.A., Jordaan, H.W.: Reward signal design for autonomous racing. In: 20th International Conference on Advanced Robotics, ICAR 2021, Ljubljana, Slovenia, 6\u201310 Dec 2021, pp. 455\u2013460. IEEE (2021)","DOI":"10.1109\/ICAR53236.2021.9659438"},{"key":"18_CR16","unstructured":"Fujimoto, S., Hoof, H.V., Meger, D.: Addressing function approximation error in actor-critic methods. In: Jennifer, G., Dy., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 Jul 2018, vol. 80 of Proceedings of Machine Learning Research, pp. 1582\u20131591. PMLR (2018)"},{"key":"18_CR17","unstructured":"Galletti, G.: Deep reinforcement learning nell\u2019ambiente pytorcs. Master\u2019s thesis, University of Bologna, school of Science, Session III 2021"},{"issue":"1","key":"18_CR18","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MCS.2018.2876958","volume":"39","author":"B Goldfain","year":"2019","unstructured":"Goldfain, B., et al.: AutoRally: an open platform for aggressive autonomous driving. IEEE Control Syst. Mag. 39(1), 26\u201355 (2019)","journal-title":"IEEE Control Syst. Mag."},{"key":"18_CR19","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 Jul 2018, vol. 80 of Proceedings of Machine Learning Research, pp. 1856\u20131865. PMLR (2018)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Herman, J., et al.: Learn-to-Race: a multimodal control environment for autonomous racing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9793\u20139802 (2021)","DOI":"10.1109\/ICCV48922.2021.00965"},{"key":"18_CR21","unstructured":"Li, C.: Challenging on car racing problem from openai gym. arXiv preprint arXiv:abs\/1911.04868 (2019)"},{"key":"18_CR22","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2\u20134 May 2016, Conference Track Proceedings (2016)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Loiacono, D., et al.: The 2009 simulated car racing championship. IEEE Trans. Comput. Intell. AI Games 2(2), 131\u2013147 (2010)","DOI":"10.1109\/TCIAIG.2010.2050590"},{"key":"18_CR24","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:abs\/1312.5602 (2013)"},{"issue":"7540","key":"18_CR25","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":"18_CR26","doi-asserted-by":"crossref","unstructured":"Paull, L., et al.: Duckietown: an open, inexpensive and flexible platform for autonomy education and research. In: 2017 IEEE International Conference on Robotics and Automation, ICRA 2017, Singapore, Singapore, May 29 - June 3, 2017, pp. 1497\u20131504 (2017)","DOI":"10.1109\/ICRA.2017.7989179"},{"key":"18_CR27","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net (2018)"},{"key":"18_CR28","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:abs\/1707.06347 (2017)"},{"key":"18_CR29","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.A.: Deterministic policy gradient algorithms. In: Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21\u201326 June 2014, vol. 32 of JMLR Workshop and Conference Proceedings, pp. 387\u2013395. JMLR.org (2014)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Singh, S.P., Barto, A.G., Chentanez, N.: Intrinsically motivated reinforcement learning. In: Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, NIPS 2004, December 13\u201318, 2004, Vancouver, British Columbia, Canada], pp. 1281\u20131288 (2004)","DOI":"10.21236\/ADA440280"},{"key":"18_CR31","volume-title":"Sutton and Andrew G","author":"S Richard","year":"1998","unstructured":"Richard, S.: Sutton and Andrew G, 1st edn. Barto. Introduction to Reinforcement Learning. MIT Press, Cambridge, MA, USA (1998)","edition":"1"},{"key":"18_CR32","series-title":"Studies in Systems, Decision and Control","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0","volume-title":"Handbook of Reinforcement Learning and Control","year":"2021","unstructured":"Vamvoudakis, K.G., Wan, Y., Lewis, F.L., Cansever, D. (eds.): Handbook of Reinforcement Learning and Control. SSDC, vol. 325. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-60990-0"},{"key":"18_CR33","unstructured":"Vorabbi, S.: Analisi dell\u2019ambiente aws deepracer per la sperimentazione di tecniche di reinforcement learning. Master\u2019s thesis, University of Bologna, school of Science, Session II 2021"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Deep reinforcement learning: a survey. Frontiers Inf. Technol. Electron. Eng. 21(12), 1726\u20131744 (2020)","DOI":"10.1631\/FITEE.1900533"}],"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\/978-3-031-25599-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:12:15Z","timestamp":1680714735000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25599-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031255984","9783031255991"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25599-1_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 March 2023","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":"Certosa di Pontignano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lod2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2022.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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"226","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":"85","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":"38% - 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":"1.5","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)"}}]}}