{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T07:26:45Z","timestamp":1767166005860,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819958368"},{"type":"electronic","value":"9789819958375"}],"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\/978-981-99-5837-5_4","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T01:01:29Z","timestamp":1693789289000},"page":"40-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Structural and\u00a0Compact Latent Representation Learning on\u00a0Sparse Reward Environments"],"prefix":"10.1007","author":[{"given":"Bang-Giang","family":"Le","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thi-Linh","family":"Hoang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai-Dang","family":"Kieu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viet-Cuong","family":"Ta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"4_CR1","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"4_CR2","first-page":"10674","volume":"35","author":"D Yarats","year":"2021","unstructured":"Yarats, D., Zhang, A., Kostrikov, I., Amos, B., Pineau, J., Fergus, R.: Improving sample efficiency in model-free reinforcement learning from images. Proc. AAAI Conf. Artif. Intell. 35, 10674\u201310681 (2021)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"4_CR3","unstructured":"Shelhamer, E., Mahmoudieh, P., Argus, M., Darrell, T.: Loss is its own reward: self-supervision for reinforcement learning. arXiv preprint arXiv:1612.07307 (2016)"},{"key":"4_CR4","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"4_CR5","unstructured":"Higgins, I., et al.: Beta-vae: learning basic visual concepts with a constrained variational framework (2016)"},{"key":"4_CR6","unstructured":"Kim, H., Kim, J., Jeong, Y., Levine, S. and Song, H.O.: Emi: exploration with mutual information. arXiv preprint arXiv:1810.01176 (2018)"},{"key":"4_CR7","first-page":"5565","volume":"33","author":"A Ermolov","year":"2020","unstructured":"Ermolov, A., Sebe, N.: Latent world models for intrinsically motivated exploration. Adv. Neural Inf. Process. Syst. 33, 5565\u20135575 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4_CR8","unstructured":"Tang, H., et al.: # exploration: a study of count-based exploration for deep reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"4_CR9","unstructured":"Stadie, B.C., Levine, S., Abbeel, P.: Incentivizing exploration in reinforcement learning with deep predictive models. arXiv preprint arXiv:1507.00814 (2015)"},{"key":"4_CR10","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, vol. 29 (2016)"},{"key":"4_CR11","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"key":"4_CR12","first-page":"9663","volume":"34","author":"T Zhang","year":"2021","unstructured":"Zhang, T., Rashidinejad, P., Jiao, J., Tian, Y., Gonzalez, J.E., Russell, S.: Exploration via maximizing deviation from explored regions. Adv. Neural Inf. Process. Syst. 34, 9663\u20139680 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4_CR13","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"4_CR14","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Visual reinforcement learning with imagined goals. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"4_CR15","unstructured":"Zhang, A., McAllister, R., Calandra, R., Gal, Y., Levine, S.: Learning invariant representations for reinforcement learning without reconstruction. arXiv preprint arXiv:2006.10742 (2020)"},{"key":"4_CR16","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"issue":"3","key":"4_CR17","first-page":"279","volume":"8","author":"JCH Christopher","year":"1992","unstructured":"Christopher, J.C.H.: Christopher JCH watkins and peter dayan: q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"4_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"4_CR19","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press, Cambridge (2018)"},{"key":"4_CR20","unstructured":"Han, S., Sung, Y.: Diversity actor-critic: sample-aware entropy regularization for sample-efficient exploration. In: International Conference on Machine Learning, pp. 4018\u20134029. PMLR (2021)"},{"key":"4_CR21","unstructured":"Savinov, N., et al.: Episodic curiosity through reachability. arXiv preprint arXiv:1810.02274 (2018)"},{"key":"4_CR22","unstructured":"Raileanu, R., Rockt\u00e4schel, T.: Ride: rewarding impact-driven exploration for procedurally-generated environments. arXiv preprint arXiv:2002.12292 (2020)"},{"key":"4_CR23","unstructured":"Kostrikov, I., Yarats, D., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. arXiv preprint arXiv:2004.13649 (2020)"},{"key":"4_CR24","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for gymnasium (2018)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-5837-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T07:22:30Z","timestamp":1767165750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-5837-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819958368","9789819958375"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-5837-5_4","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":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phuket","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"24 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}