{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:59:11Z","timestamp":1774663151440,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698936","type":"print"},{"value":"9789819698943","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\/978-981-96-9894-3_10","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T19:56:59Z","timestamp":1753473419000},"page":"108-121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SRPPO: Stein Self-repulsive Proximal Policy Optimization for Effective Policy Diversity in Single-Chain Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7805-3300","authenticated-orcid":false,"given":"Tianyu","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongchun","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyue","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Tang, C., Abbatematteo, B., Hu, J., Chandra, R., Mart\u00edn-Mart\u00edn, R., Stone, P.: Deep reinforcement learning for robotics: a survey of real-world successes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 28694\u2013 28698 (2025)","DOI":"10.1609\/aaai.v39i27.35095"},{"key":"10_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.03.003","volume":"85","author":"P Ladosz","year":"2022","unstructured":"Ladosz, P., Weng, L., Kim, M., Oh, H.: Exploration in deep reinforcement learning: a survey. Inf. Fus. 85, 1\u201322 (2022)","journal-title":"Inf. Fus."},{"key":"10_CR3","unstructured":"Rietz, F., Stork, J.A.: Diversity for contingency: learning diverse behaviors for efficient adaptation and transfer. arXiv preprint arXiv:2310.07493 (2023)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Pateria, S., Subagdja, B., Tan, A.H., Quek, C.: Hierarchical reinforcement learning: a comprehensive survey. ACM Comput. Surv. (CSUR) 54(5), 1\u201335 (2021)","DOI":"10.1145\/3453160"},{"key":"10_CR5","unstructured":"Houthooft, R., Chen, X., Duan, Y., Schulman, J., De Turck, F., Abbeel, P.: VIME: variational information maximizing exploration. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"10_CR6","unstructured":"Liu, Y., Ramachandran, P., Liu, Q., Peng, J.: Stein variational policy gradient. arXiv preprint arXiv:1704.02399 (2017)"},{"key":"10_CR7","unstructured":"Gangwani, T., Liu, Q., Peng, J.: Learning self-imitating diverse policies. arXiv preprint arXiv:1805.10309 (2018)"},{"key":"10_CR8","unstructured":"Gangwani, T., Peng, J., Zhou, Y.: Harnessing distribution ratio estimators for learning agents with quality and diversity. In: Conference on Robot Learning, pp. 2206\u20132215. PMLR (2021)"},{"key":"10_CR9","unstructured":"Liu, Q., Wang, D.: Stein variational gradient descent as moment matching. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"10_CR10","first-page":"241","volume":"33","author":"M Ye","year":"2020","unstructured":"Ye, M., Ren, T., Liu, Q.: Stein self-repulsive dynamics: benefits from past samples. Adv. Neural. Inf. Process. Syst. 33, 241\u2013252 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"10_CR11","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1111\/j.2517-6161.1966.tb00626.x","volume":"28","author":"SM Ali","year":"1966","unstructured":"Ali, S.M., Silvey, S.D.: A general class of coefficients of divergence of one distribution from another. J. Roy. Stat. Soc.: Ser. B (Methodol.) 28(1), 131\u2013142 (1966)","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"key":"10_CR12","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 297\u2013304. JMLR Workshop and Conference Proceedings (2010)"},{"key":"10_CR13","unstructured":"Nachum, O., Chow, Y., Dai, B., Li, L.: DualDICE: behavior-agnostic estimation of discounted stationary distribution corrections. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"10_CR14","unstructured":"Kostrikov, I., Nachum, O., Tompson, J.: Imitation learning via off-policy distribution matching. arXiv preprint arXiv:1912.05032 (2019)"},{"key":"10_CR15","unstructured":"Zhang, R., Dai, B., Li, L., Schuurmans, D.: GenDICE: Generalized offline estimation of stationary values. arXiv preprint arXiv:2002.09072 (2020)"},{"key":"10_CR16","unstructured":"Brockman, G.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"10_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"10_CR20","unstructured":"Mnih, V.: Asynchronous methods for deep reinforcement learning. arXiv preprint arXiv:1602.01783 (2016)"},{"key":"10_CR21","unstructured":"ilver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. PMLR (2014)"},{"key":"10_CR22","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"10_CR23","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)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9894-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:35:46Z","timestamp":1774661746000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9894-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698936","9789819698943"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9894-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}