{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:45:58Z","timestamp":1742913958220,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030616151"},{"type":"electronic","value":"9783030616168"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-61616-8_22","type":"book-chapter","created":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T23:07:42Z","timestamp":1602889662000},"page":"269-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Exploration via Progress-Driven Intrinsic Rewards"],"prefix":"10.1007","author":[{"given":"Nicolas","family":"Bougie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryutaro","family":"Ichise","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"22_CR1","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. JAIR 47, 253\u2013279 (2013)","journal-title":"JAIR"},{"issue":"3","key":"22_CR2","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/s10994-019-05845-8","volume":"109","author":"N Bougie","year":"2019","unstructured":"Bougie, N., Ichise, R.: Skill-based curiosity for intrinsically motivated reinforcement learning. Mach. Learn. 109(3), 493\u2013512 (2019). https:\/\/doi.org\/10.1007\/s10994-019-05845-8","journal-title":"Mach. Learn."},{"key":"22_CR3","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint:1810.12894 (2018)"},{"key":"22_CR4","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for openAI gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"22_CR5","unstructured":"Florensa, C., Held, D., Geng, X., Abbeel, P.: Automatic goal generation for reinforcement learning agents. arXiv preprint:1705.06366 (2017)"},{"key":"22_CR6","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint:1801.01290 (2018)"},{"key":"22_CR7","unstructured":"Hong, Z.W., Shann, T.Y., Su, S.Y., Chang, Y.H., Fu, T.J., Lee, C.Y.: Diversity-driven exploration strategy for deep reinforcement learning. In: NIPS (2018)"},{"key":"22_CR8","unstructured":"Houthooft, R., Chen, X., Duan, Y., Schulman, J., De Turck, F., Abbeel, P.: Variational information maximizing exploration. In: NIPS, pp. 1109\u20131117 (2016)"},{"key":"22_CR9","unstructured":"Kaelbling, L.P.: Learning to achieve goals. In: IJCAI, pp. 1094\u20131098 (1993)"},{"key":"22_CR10","unstructured":"Kauten, C.: Super mario bros for openAI gym. https:\/\/github.com\/Kautenja\/gym-super-mario-bros (2018)"},{"key":"22_CR11","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)"},{"key":"22_CR12","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint:1509.02971 (2015)"},{"key":"22_CR13","unstructured":"Machado, M., Bellemare, M., Bowling, M.: Count-based exploration with the successor representation. arXiv preprint:1807.11622 (2018)"},{"key":"22_CR14","unstructured":"Mnih, V., et al.: Asynchronous methods for DRL. In: ICML, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"22_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 (2015)","journal-title":"Nature"},{"key":"22_CR16","unstructured":"Nair, A.V., Pong, V., Dalal, M., Bahl, S., Lin, S., Levine, S.: Visual reinforcement learning with imagined goals. In: ICML, pp. 9191\u20139200 (2018)"},{"key":"22_CR17","unstructured":"Ostrovski, G., Bellemare, M.G., van den Oord, A., Munos, R.: Count-based exploration with neural density models. In: ICML, pp. 2721\u20132730 (2017)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: ICML (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"22_CR19","unstructured":"Savinov, N., et al.: Episodic curiosity through reachability. In: ICLR (2019)"},{"key":"22_CR20","unstructured":"Schaul, T., Horgan, D., Gregor, K., Silver, D.: Universal value function approximators. In: Proceedings of the International conference on Machine Learning (2015)"},{"key":"22_CR21","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint:1707.06347 (2017)"},{"key":"22_CR22","unstructured":"Stanton, C., Clune, J.: Deep curiosity search: intra-life exploration improves performance on challenging deep reinforcement learning problems. In: ICML (2019)"},{"key":"22_CR23","unstructured":"Tang, H., et al.: Exploration: a study of count-based exploration for deep reinforcement learning. In: NIPS, pp. 2753\u20132762 (2017)"},{"key":"22_CR24","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. In: ICML (2016)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61616-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T10:20:15Z","timestamp":1619259615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-61616-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030616151","9783030616168"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61616-8_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"14 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"249","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":"139","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":"56% - 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":"2.5","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)"}},{"value":"*The conference was postponed to 2021 due to the COVID-19 pandemic.","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)"}}]}}