{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T07:40:05Z","timestamp":1750837205594,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819669530","type":"print"},{"value":"9789819669547","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-6954-7_1","type":"book-chapter","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T07:00:44Z","timestamp":1750834844000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Efficiency of\u00a0Unsupervised Skill Discovery by\u00a0Model Resetting Curriculum"],"prefix":"10.1007","author":[{"given":"Yuanjiang","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan.Z.","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"1_CR1","unstructured":"Achiam, J., Edwards, H., Amodei, D., Abbeel, P.: Variational option discovery algorithms. arXiv preprint arXiv:1807.10299 (2018)"},{"issue":"7","key":"1_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3543846","volume":"55","author":"MM Afsar","year":"2022","unstructured":"Afsar, M.M., Crump, T., Far, B.: Reinforcement learning based recommender systems: a survey. ACM Comput. Surv. 55(7), 1\u201338 (2022)","journal-title":"ACM Comput. Surv."},{"key":"1_CR3","unstructured":"Ash, J., Adams, R.P.: On warm-starting neural network training. In: Advances in Neural Information Processing Systems, vol. 33, pp. 3884\u20133894 (2020)"},{"key":"1_CR4","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"1_CR5","unstructured":"Campos, V., Trott, A., Xiong, C., Socher, R., Gir\u00f3-i Nieto, X., Torres, J.: Explore, discover and learn: Unsupervised discovery of state-covering skills. In: International Conference on Machine Learning, pp. 1317\u20131327. PMLR (2020)"},{"key":"1_CR6","unstructured":"Cao, Y., Yao, L., McAuley, J., Sheng, Q.Z.: Reinforcement learning for generative AI: a survey. arXiv preprint arXiv:2308.14328 (2023)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chaudhry, A., Dokania, P.K., Ajanthan, T., Torr, P.H.: Riemannian walk for incremental learning: understanding forgetting and intransigence. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 532\u2013547 (2018)","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"1_CR8","unstructured":"Choi, J., Sharma, A., Lee, H., Levine, S., Gu, S.S.: Variational empowerment as representation learning for goal-conditioned reinforcement learning. In: International Conference on Machine Learning, pp. 1953\u20131963. PMLR (2021)"},{"key":"1_CR9","unstructured":"D\u2019Oro, P., Schwarzer, M., Nikishin, E., Bacon, P.L., Bellemare, M.G., Courville, A.: Sample-efficient reinforcement learning by breaking the replay ratio barrier. In: Deep Reinforcement Learning Workshop NeurIPS 2022 (2022)"},{"key":"1_CR10","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., Levine, S.: Diversity is all you need: learning skills without a reward function. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=SJx63jRqFm"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Fang, K., Migimatsu, T., Mandlekar, A., Fei-Fei, L., Bohg, J.: Active task randomization: learning robust skills via unsupervised generation of diverse and feasible tasks. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.\u00a01\u20138. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10341727"},{"issue":"3","key":"1_CR12","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/0005-1098(89)90002-2","volume":"25","author":"CE Garcia","year":"1989","unstructured":"Garcia, C.E., Prett, D.M., Morari, M.: Model predictive control: theory and practice\u2013a survey. Automatica 25(3), 335\u2013348 (1989)","journal-title":"Automatica"},{"key":"1_CR13","unstructured":"Gregor, K., Rezende, D.J., Wierstra, D.: Variational intrinsic control. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Workshop Track Proceedings. OpenReview.net (2017). https:\/\/openreview.net\/forum?id=Skc-Fo4Yg"},{"key":"1_CR14","unstructured":"Haarnoja, T., et\u00a0al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"},{"key":"1_CR15","unstructured":"Hansen, S., Dabney, W., Barreto, A., Warde-Farley, D., de\u00a0Wiele, T.V., Mnih, V.: Fast task inference with variational intrinsic successor features. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=BJeAHkrYDS"},{"key":"1_CR16","unstructured":"Kim, J., Park, S., Kim, G.: Unsupervised skill discovery with bottleneck option learning. arXiv preprint arXiv:2106.14305 (2021)"},{"key":"1_CR17","unstructured":"Lee, L., Eysenbach, B., Parisotto, E., Xing, E., Levine, S., Salakhutdinov, R.: Efficient exploration via state marginal matching. arXiv preprint arXiv:1906.05274 (2019)"},{"key":"1_CR18","unstructured":"Liu, H., Abbeel, P.: APS: active pretraining with successor features. In: International Conference on Machine Learning, pp. 6736\u20136747. PMLR (2021)"},{"key":"1_CR19","unstructured":"Liu, H., Abbeel, P.: Behavior from the void: unsupervised active pre-training. In: Advances in Neural Information Processing Systems, vol. 34, pp. 18459\u201318473 (2021)"},{"key":"1_CR20","unstructured":"Nikishin, E., Schwarzer, M., D\u2019Oro, P., Bacon, P.L., Courville, A.: The primacy bias in deep reinforcement learning. In: International Conference on Machine Learning, pp. 16828\u201316847. PMLR (2022)"},{"key":"1_CR21","unstructured":"Park, S., Choi, J., Kim, J., Lee, H., Kim, G.: Lipschitz-constrained unsupervised skill discovery. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=BGvt0ghNgA"},{"key":"1_CR22","unstructured":"Park, S., Lee, K., Lee, Y., Abbeel, P.: Controllability-aware unsupervised skill discovery. arXiv preprint arXiv:2302.05103 (2023)"},{"key":"1_CR23","unstructured":"Park, S., Rybkin, O., Levine, S.: Metra: scalable unsupervised RL with metric-aware abstraction. arXiv preprint arXiv:2310.08887 (2023)"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Rudin, N., Hoeller, D., Bjelonic, M., Hutter, M.: Advanced skills by learning locomotion and local navigation end-to-end. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2497\u20132503. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"1_CR25","unstructured":"Sharma, A., Gu, S., Levine, S., Kumar, V., Hausman, K.: Dynamics-aware unsupervised discovery of skills. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=HJgLZR4KvH"},{"key":"1_CR26","unstructured":"Silver, D., et\u00a0al.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815 (2017)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Tan, J., Senanayake, R., Ramos, F.: Renaissance robot: optimal transport policy fusion for learning diverse skills. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7052\u20137059. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981105"},{"key":"1_CR28","unstructured":"Zhang, J., Yu, H., Xu, W.: Hierarchical reinforcement learning by discovering intrinsic options. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=r-gPPHEjpmw"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6954-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T07:00:58Z","timestamp":1750834858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6954-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819669530","9789819669547"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6954-7_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}