{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:23:56Z","timestamp":1743063836344,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030731120"},{"type":"electronic","value":"9783030731137"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-73113-7_10","type":"book-chapter","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T15:03:19Z","timestamp":1626966199000},"page":"109-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Intrinsically Motivated Lifelong Exploration in Reinforcement Learning"],"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":[[2021,7,23]]},"reference":[{"key":"10_CR1","unstructured":"Abel, D., Agarwal, A., Diaz, F., Krishnamurthy, A., Schapire, R.E.: Exploratory gradient boosting for reinforcement learning in complex domains. In: ICML Workshop on Abstraction in Reinforcement Learning (2016)"},{"key":"10_CR2","unstructured":"Badia, A.P., et al.: Never give up: learning directed exploration strategies. In: International Conference on Learning Representations (2020)"},{"key":"10_CR3","unstructured":"Beattie, C., et al.: DeepMind lab. arXiv preprint arXiv:1612.03801 (2016)"},{"key":"10_CR4","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Advances in Neural Information Processing Systems, pp. 1471\u20131479 (2016)"},{"key":"10_CR5","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":"10_CR6","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, 493\u2013512 (2019)","journal-title":"Mach. Learn."},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Bougie, N., Ichise, R.: Combining local and global exploration via intrinsic rewards. In: Annual Conference of JSAI, pp. 2K6ES205\u20132K6ES205 (2020). https:\/\/doi.org\/10.11517\/pjsai.JSAI2020.0_2K6ES205","DOI":"10.11517\/pjsai.JSAI2020.0_2K6ES205"},{"key":"10_CR8","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. In: Conference on Learning Representations (2019)"},{"key":"10_CR9","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for OpenAI gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"10_CR10","unstructured":"Fu, J., Co-Reyes, J., Levine, S.: Ex2: exploration with exemplar models for deep reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2577\u20132587 (2017)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Han, D.: Comparison of commonly used image interpolation methods. In: Conference on Computer Science and Electronics Engineering (2013)","DOI":"10.2991\/iccsee.2013.391"},{"key":"10_CR12","unstructured":"Houthooft, R., et al.: VIME: variational information maximizing exploration. In: Advances in Neural Information Processing Systems, pp. 1109\u20131117 (2016)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Klyubin, A.S., Polani, D., Nehaniv, C.L.: Empowerment: a universal agent-centric measure of control. In: IEEE Congress on Evolutionary Computation, vol. 1, pp. 128\u2013135 (2005)","DOI":"10.1109\/CEC.2005.1554676"},{"key":"10_CR14","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1162\/EVCO_a_00025","volume":"19","author":"J Lehman","year":"2011","unstructured":"Lehman, J., Stanley, K.O.: Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19, 189\u2013223 (2011)","journal-title":"Evol. Comput."},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Machado, M.C., Bellemare, M.G., Bowling, M.: Count-based exploration with the successor representation. In: AAAI Conference on Artificial Intelligence, pp. 5125\u20135133 (2020)","DOI":"10.1609\/aaai.v34i04.5955"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Martin, J., Sasikumar, S.N., Everitt, T., Hutter, M.: Count-based exploration in feature space for reinforcement learning. In: International Joint Conference on Artificial Intelligence (2017)","DOI":"10.24963\/ijcai.2017\/344"},{"key":"10_CR17","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"10_CR18","unstructured":"Ostrovski, G., Bellemare, M.G., van den Oord, A., Munos, R.: Count-based exploration with neural density models. In: International Conference on Machine Learning, pp. 2721\u20132730 (2017)"},{"key":"10_CR19","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 International Conference on Machine Learning (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"10_CR20","unstructured":"Raileanu, R., Rockt\u00e4schel, T.: Ride: rewarding impact-driven exploration for procedurally-generated environments. In: International Conference on Learning Representations (2020)"},{"key":"10_CR21","unstructured":"Savinov, N., et al.: Episodic curiosity through reachability. In: International Conference on Learning Representations (2019)"},{"key":"10_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"8","key":"10_CR23","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"AL Strehl","year":"2008","unstructured":"Strehl, A.L., Littman, M.L.: An analysis of model-based interval estimation for Markov decision processes. J. Comput. Syst. Sci. 74(8), 1309\u20131331 (2008)","journal-title":"J. Comput. Syst. Sci."},{"key":"10_CR24","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"10_CR25","unstructured":"Tang, H., et al.: # exploration: a study of count-based exploration for deep reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2753\u20132762 (2017)"},{"issue":"4","key":"10_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR27","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning (2016)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Yang, H.K., Chiang, P.H., Hong, M.F., Lee, C.Y.: Flow-based intrinsic curiosity module. In: Proceedings of the the International Conference on Learning Representations (2020)","DOI":"10.24963\/ijcai.2020\/286"}],"container-title":["Advances in Intelligent Systems and Computing","Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-73113-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:13:40Z","timestamp":1725484420000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-73113-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030731120","9783030731137"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-73113-7_10","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"JSAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Annual Conference of the Japanese Society for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kumamoto-ken","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"9 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"jsai2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ai-gakkai.or.jp\/jsai2020\/en","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}