{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:30:03Z","timestamp":1742992203561,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031479939"},{"type":"electronic","value":"9783031479946"}],"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\/978-3-031-47994-6_18","type":"book-chapter","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T08:02:28Z","timestamp":1699344148000},"page":"216-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Novel State Space Exploration Method for\u00a0the\u00a0Sparse-Reward Reinforcement Learning Environment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7674-3183","authenticated-orcid":false,"given":"Xi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8776-9112","authenticated-orcid":false,"given":"Long","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2151-7028","authenticated-orcid":false,"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1894-722X","authenticated-orcid":false,"given":"Changgang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3626-9450","authenticated-orcid":false,"given":"Ren","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-0557","authenticated-orcid":false,"given":"Yong","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0531-2903","authenticated-orcid":false,"given":"Shufan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,8]]},"reference":[{"issue":"2","key":"18_CR1","doi-asserted-by":"publisher","first-page":"327","DOI":"10.3390\/e25020327","volume":"25","author":"A Aubret","year":"2023","unstructured":"Aubret, A., Matignon, L., Hassas, S.: An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey. Entropy 25(2), 327 (2023)","journal-title":"Entropy"},{"key":"18_CR2","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":"18_CR3","doi-asserted-by":"crossref","unstructured":"Bellman, R.: A Markovian decision process. J. Math. Mech. 679\u2013684 (1957)","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"18_CR4","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"issue":"7847","key":"18_CR5","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","volume":"590","author":"A Ecoffet","year":"2021","unstructured":"Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K.O., Clune, J.: First return, then explore. Nature 590(7847), 580\u2013586 (2021)","journal-title":"Nature"},{"key":"18_CR6","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"18_CR8","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. arXiv preprint arXiv:1803.00933 (2018)"},{"key":"18_CR9","first-page":"30432","volume":"35","author":"D Jo","year":"2022","unstructured":"Jo, D., et al.: LECO: learnable episodic count for task-specific intrinsic reward. Adv. Neural. Inf. Process. Syst. 35, 30432\u201330445 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR10","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"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. In: Wiley Series in Probability and Statistics (1994)","DOI":"10.1002\/9780470316887"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Saglam, B., Mutlu, F.B., Cicek, D.C., Kozat, S.S.: Actor prioritized experience replay. arXiv preprint arXiv:2209.00532 (2022)","DOI":"10.1613\/jair.1.14819"},{"key":"18_CR13","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"18_CR14","unstructured":"Seo, Y., Chen, L., Shin, J., Lee, H., Abbeel, P., Lee, K.: State entropy maximization with random encoders for efficient exploration. In: International Conference on Machine Learning, pp. 9443\u20139454. PMLR (2021)"},{"key":"18_CR15","unstructured":"Yu, X., Lyu, Y., Tsang, I.: Intrinsic reward driven imitation learning via generative model. In: International Conference on Machine Learning, pp. 10925\u201310935. PMLR (2020)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Yuan, M., Pun, M.O., Wang, D.: R\u00e9nyi state entropy maximization for exploration acceleration in reinforcement learning. IEEE Trans. Artif. Intell. (2022)","DOI":"10.1109\/TAI.2022.3185180"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1109\/TETCI.2021.3082204","volume":"6","author":"C Zheng","year":"2021","unstructured":"Zheng, C., Yang, S., Parra-Ullauri, J.M., Garcia-Dominguez, A., Bencomo, N.: Reward-reinforced generative adversarial networks for multi-agent systems. IEEE Trans. Emerg. Top. Comput. Intell. 6, 479\u2013488 (2021)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XL"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47994-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T11:36:33Z","timestamp":1703504193000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47994-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031479939","9783031479946"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47994-6_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":"8 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SGAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovative Techniques and Applications of Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2023\/","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":"ConferenceExpert","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"27","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":"20","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":"2 or 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","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":"A total of 76 reviewers plus two \u2018executive program committees\u2019 (one for each stream)","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)"}}]}}