{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T21:09:36Z","timestamp":1788728976219,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376695","type":"print"},{"value":"9783032376701","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-37670-1_22","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:42:30Z","timestamp":1788727350000},"page":"376-392","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quality and\u00a0Diversity Optimization Even from Offline Homogeneous Dataset"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7186-9640","authenticated-orcid":false,"given":"Ziyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1835-3707","authenticated-orcid":false,"given":"Kartik","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Sosme\u00f1a","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2072-8950","authenticated-orcid":false,"given":"Ping-Chun","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5443-470X","authenticated-orcid":false,"given":"Tzu-Mao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2550-2990","authenticated-orcid":false,"given":"Yu-Shuen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8691-975X","authenticated-orcid":false,"given":"Yun-Hsuan","family":"Lien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"22_CR1","first-page":"7436","volume":"34","author":"G An","year":"2021","unstructured":"An, G., Moon, S., Kim, J.H., Song, H.O.: Uncertainty-based offline reinforcement learning with diversified Q-ensemble. Adv. Neural. Inf. Process. Syst. 34, 7436\u20137447 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR2","unstructured":"Anand, A., Racah, E., Ozair, S., Bengio, Y., C\u00f4t\u00e9, M.A., Hjelm, R.D.: Unsupervised state representation learning in Atari. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"22_CR3","first-page":"17007","volume":"34","author":"C Bai","year":"2021","unstructured":"Bai, C., et al.: Dynamic bottleneck for robust self-supervised exploration. Adv. Neural. Inf. Process. Syst. 34, 17007\u201317020 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR4","doi-asserted-by":"publisher","first-page":"67925","DOI":"10.52202\/075280-2971","volume":"36","author":"J Chen","year":"2023","unstructured":"Chen, J., Aggarwal, V., Lan, T.: A unified algorithm framework for unsupervised discovery of skills based on determinantal point process. Adv. Neural. Inf. Process. Syst. 36, 67925\u201367947 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"22_CR5","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1109\/TEVC.2017.2704781","volume":"22","author":"A Cully","year":"2017","unstructured":"Cully, A., Demiris, Y.: Quality and diversity optimization: a unifying modular framework. IEEE Trans. Evol. Comput. 22(2), 245\u2013259 (2017)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"22_CR6","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":"22_CR7","first-page":"10040","volume":"34","author":"M Fontaine","year":"2021","unstructured":"Fontaine, M., Nikolaidis, S.: Differentiable quality diversity. Adv. Neural. Inf. Process. Syst. 34, 10040\u201310052 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR8","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4RL: datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 (2020)"},{"key":"22_CR9","first-page":"20132","volume":"34","author":"S Fujimoto","year":"2021","unstructured":"Fujimoto, S., Gu, S.S.: A minimalist approach to offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 20132\u201320145 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR10","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":"22_CR11","unstructured":"Hong, Z.W., Shann, T.Y., Su, S.Y., Chang, Y.H., Fu, T.J., Lee, C.Y.: Diversity-driven exploration strategy for deep reinforcement learning. Adv. Neural. Inf. Process. Syst. 31 (2018)"},{"key":"22_CR12","first-page":"15931","volume":"33","author":"Y Hu","year":"2020","unstructured":"Hu, Y., et al.: Learning to utilize shaping rewards: a new approach of reward shaping. Adv. Neural. Inf. Process. Syst. 33, 15931\u201315941 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR13","unstructured":"Jaques, N., et al.: Social influence as intrinsic motivation for multi-agent deep reinforcement learning. In: International Conference on Machine Learning, pp. 3040\u20133049. PMLR (2019)"},{"key":"22_CR14","unstructured":"Jiang, J., Lu, Z.: The emergence of individuality. In: International Conference on Machine Learning, pp. 4992\u20135001. PMLR (2021)"},{"key":"22_CR15","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. IEEE (2005)","DOI":"10.1109\/CEC.2005.1554676"},{"issue":"12","key":"22_CR16","doi-asserted-by":"publisher","first-page":"e4018","DOI":"10.1371\/journal.pone.0004018","volume":"3","author":"AS Klyubin","year":"2008","unstructured":"Klyubin, A.S., Polani, D., Nehaniv, C.L.: Keep your options open: an information-based driving principle for sensorimotor systems. PLoS ONE 3(12), e4018 (2008)","journal-title":"PLoS ONE"},{"key":"22_CR17","unstructured":"Konan, S.G., Seraj, E., Gombolay, M.: Iterated reasoning with mutual information in cooperative and byzantine decentralized teaming. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=giBFoa-uS12"},{"key":"22_CR18","unstructured":"Kostrikov, I., Fergus, R., Tompson, J., Nachum, O.: Offline reinforcement learning with fisher divergence critic regularization. In: International Conference on Machine Learning, pp. 5774\u20135783. PMLR (2021)"},{"key":"22_CR19","unstructured":"Kumar, A., Fu, J., Soh, M., Tucker, G., Levine, S.: Stabilizing off-policy Q-learning via bootstrapping error reduction. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"22_CR20","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Laskin, M., et al.: Contrastive intrinsic control for unsupervised reinforcement learning. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 34478\u201334491 (2022)","DOI":"10.52202\/068431-2498"},{"key":"22_CR22","unstructured":"Leibfried, F., Pascual-Diaz, S., Grau-Moya, J.: A unified bellman optimality principle combining reward maximization and empowerment. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"22_CR23","first-page":"3991","volume":"34","author":"C Li","year":"2021","unstructured":"Li, C., Wang, T., Wu, C., Zhao, Q., Yang, J., Zhang, C.: Celebrating diversity in shared multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 3991\u20134002 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR24","unstructured":"Li, Y., Song, J., Ermon, S.: InfoGAIL: interpretable imitation learning from visual demonstrations. Adv. Neural. Inf. Process. Syst. 30 (2017)"},{"key":"22_CR25","unstructured":"Liu, J., Zu, L., He, L., Wang, D.: CLUE: calibrated latent guidance for offline reinforcement learning. In: Conference on Robot Learning, pp. 906\u2013927. PMLR (2023)"},{"key":"22_CR26","doi-asserted-by":"publisher","first-page":"10339","DOI":"10.52202\/068431-0751","volume":"35","author":"Z Liu","year":"2022","unstructured":"Liu, Z., Yu, C., Yang, Y., Wu, Z., Li, Y., et al.: A unified diversity measure for multiagent reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 10339\u201310352 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR27","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1016\/j.ins.2022.08.019","volume":"610","author":"X Lou","year":"2022","unstructured":"Lou, X., et al.: Offline reinforcement learning with representations for actions. Inf. Sci. 610, 746\u2013758 (2022)","journal-title":"Inf. Sci."},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"19058","DOI":"10.52202\/075280-0835","volume":"36","author":"X Ma","year":"2023","unstructured":"Ma, X., Kang, B., Xu, Z., Lin, M., Yan, S.: Mutual information regularized offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 19058\u201319072 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR29","unstructured":"Mao, Y., et\u00a0al.: Stylized offline reinforcement learning: extracting diverse high-quality behaviors from heterogeneous datasets. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"22_CR30","unstructured":"Mazoure, B., Tachet des Combes, R., Doan, T.L., Bachman, P., Hjelm, R.D.: Deep reinforcement and infomax learning. Adv. Neural. Inf. Process. Syst. 33, 3686\u20133698 (2020)"},{"key":"22_CR31","unstructured":"Mohamed, S., Jimenez Rezende, D.: Variational information maximisation for intrinsically motivated reinforcement learning. Adv. Neural. Inf. Process. Syst. 28 (2015)"},{"key":"22_CR32","unstructured":"Nachum, O., Gu, S., Lee, H., Levine, S.: Near-optimal representation learning for hierarchical reinforcement learning. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=H1emus0qF7"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Nilsson, O., Cully, A.: Policy gradient assisted map-elites. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 866\u2013875 (2021)","DOI":"10.1145\/3449639.3459304"},{"key":"22_CR34","unstructured":"Osa, T., Harada, T.: Discovering multiple solutions from a single task in offline reinforcement learning. In: Forty-First International Conference on Machine Learning (2024). https:\/\/openreview.net\/forum?id=j6rG1ETRyu"},{"key":"22_CR35","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.neunet.2022.04.009","volume":"152","author":"T Osa","year":"2022","unstructured":"Osa, T., Tangkaratt, V., Sugiyama, M.: Discovering diverse solutions in deep reinforcement learning by maximizing state-action-based mutual information. Neural Netw. 152, 90\u2013104 (2022)","journal-title":"Neural Netw."},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Pierrot, T., et al.: Diversity policy gradient for sample efficient quality-diversity optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1075\u20131083 (2022)","DOI":"10.1145\/3512290.3528845"},{"key":"22_CR37","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3389\/frobt.2016.00040","volume":"3","author":"JK Pugh","year":"2016","unstructured":"Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016)","journal-title":"Front. Robot. AI"},{"key":"22_CR38","unstructured":"Schwarzer, M., Anand, A., Goel, R., Hjelm, R.D., Courville, A., Bachman, P.: Data-efficient reinforcement learning with self-predictive representations. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=uCQfPZwRaUu"},{"key":"22_CR39","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"},{"issue":"3","key":"22_CR40","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s12064-011-0142-z","volume":"131","author":"S Still","year":"2012","unstructured":"Still, S., Precup, D.: An information-theoretic approach to curiosity-driven reinforcement learning. Theory Biosci. 131(3), 139\u2013148 (2012)","journal-title":"Theory Biosci."},{"key":"22_CR41","unstructured":"Stooke, A., Lee, K., Abbeel, P., Laskin, M.: Decoupling representation learning from reinforcement learning. In: International Conference on Machine Learning, pp. 9870\u20139879. PMLR (2021)"},{"key":"22_CR42","first-page":"8114","volume":"33","author":"RY Tao","year":"2020","unstructured":"Tao, R.Y., Fran\u00e7ois-Lavet, V., Pineau, J.: Novelty search in representational space for sample efficient exploration. Adv. Neural. Inf. Process. Syst. 33, 8114\u20138126 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR43","unstructured":"Wang, T., Wang, J., Wu, Y., Zhang, C.: Influence-based multi-agent exploration. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=BJgy96EYvr"},{"key":"22_CR44","first-page":"7768","volume":"33","author":"Z Wang","year":"2020","unstructured":"Wang, Z., et al.: Critic regularized regression. Adv. Neural. Inf. Process. Syst. 33, 7768\u20137778 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR45","unstructured":"Wu, Y., Tucker, G., Nachum, O.: Behavior regularized offline reinforcement learning (2020). https:\/\/openreview.net\/forum?id=BJg9hTNKPH"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37670-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:42:34Z","timestamp":1788727354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37670-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"ISBN":["9783032376695","9783032376701"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37670-1_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"assertion":[{"value":"7 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}