{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:31:35Z","timestamp":1743039095461,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"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_14","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"181-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Reward Function Using Image Processing for\u00a0a\u00a0Deep Reinforcement Learning Approach Applied to\u00a0the\u00a0Sonic the\u00a0Hedgehog Game"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7675-9847","authenticated-orcid":false,"given":"Felipe Rafael","family":"de Souza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-1626","authenticated-orcid":false,"given":"Thiago Silva","family":"Miranda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2012-7802","authenticated-orcid":false,"given":"Heder Soares","family":"Bernardino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","first-page":"103500","DOI":"10.1016\/j.artint.2021.103500","volume":"297","author":"S Arora","year":"2021","unstructured":"Arora, S., Doshi, P.: A survey of inverse reinforcement learning: challenges, methods and progress. Artif. Intell. 297, 103500 (2021)","journal-title":"Artif. Intell."},{"key":"14_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"key":"14_CR3","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. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"14_CR4","unstructured":"Bradski, G., Kaehler, A.: Learning OpenCV: Computer vision with the OpenCV library. O\u2019Reilly Media, Inc. (2008)"},{"key":"14_CR5","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"14_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1007\/978-3-642-15561-1_56","volume-title":"Computer Vision \u2013 ECCV 2010","author":"M Calonder","year":"2010","unstructured":"Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: binary robust independent elementary features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 778\u2013792. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_56"},{"issue":"3","key":"14_CR7","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s40869-019-00089-x","volume":"9","author":"I Chiang","year":"2020","unstructured":"Chiang, I., Huang, C.M., Cheng, N.H., Liu, H.Y., Tsai, S.C., et al.: Efficient exploration in side-scrolling video games with trajectory replay. Comput. Games J. 9(3), 263\u2013280 (2020)","journal-title":"Comput. Games J."},{"key":"14_CR8","unstructured":"Dewey, D.: Reinforcement learning and the reward engineering principle. In: 2014 AAAI Spring Symposium Series (2014)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Fayjie, A.R., Hossain, S., Oualid, D., Lee, D.J.: Driverless car: autonomous driving using deep reinforcement learning in urban environment. In: 2018 15th International Conference on Ubiquitous Robots (UR), pp. 896\u2013901. IEEE (2018)","DOI":"10.1109\/URAI.2018.8441797"},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"14_CR11","unstructured":"Laud, A.D.: Theory and Application of Reward Shaping in Reinforcement Learning. University of Illinois at Urbana-Champaign (2004)"},{"key":"14_CR12","unstructured":"Li, Y.: Deep reinforcement learning: an overview. arXiv preprint arXiv:1701.07274 (2017)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150\u20131157. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"issue":"2","key":"14_CR14","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"issue":"91\u2013110","key":"14_CR15","first-page":"2","volume":"2","author":"G Lowe","year":"2004","unstructured":"Lowe, G.: Sift-the scale invariant feature transform. Int. J. 2(91\u2013110), 2 (2004)","journal-title":"Int. J."},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"McKnight, P.E., Najab, J.: Mann-Whitney U test. Corsini Encycl. Psychol. pp. 1\u20131 (2010)","DOI":"10.1002\/9780470479216.corpsy0524"},{"issue":"7540","key":"14_CR17","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":"14_CR18","unstructured":"Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. VISAPP (1) 2(331\u2013340), 2 (2009)"},{"key":"14_CR19","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, vol. 99, pp. 278\u2013287 (1999)"},{"key":"14_CR20","unstructured":"Nichol, A., Pfau, V., Hesse, C., Klimov, O., Schulman, J.: Gotta learn fast: a new benchmark for generalization in RL. arXiv preprint arXiv:1804.03720 (2018)"},{"key":"14_CR21","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"issue":"268","key":"14_CR23","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/11744023_34","volume-title":"Computer Vision \u2013 ECCV 2006","author":"E Rosten","year":"2006","unstructured":"Rosten, E., Drummond, T.: Machine learning for high-speed corner detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 430\u2013443. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_34"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to sift or surf. In: 2011 International Conference on Computer Vision, pp. 2564\u20132571. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"14_CR26","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"14_CR27","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"14_CR28","unstructured":"Shao, K., Tang, Z., Zhu, Y., Li, N., Zhao, D.: A survey of deep reinforcement learning in video games. arXiv preprint arXiv:1912.10944 (2019)"},{"issue":"7587","key":"14_CR29","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"14_CR30","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"}],"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_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:12:56Z","timestamp":1668989576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_14","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)"}}]}}