{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:24:53Z","timestamp":1775082293702,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584048","type":"print"},{"value":"9789819584055","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-8405-5_30","type":"book-chapter","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:18Z","timestamp":1775074518000},"page":"555-570","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ERL-CDR: Evolutionary Reinforcement Learning with\u00a0Causal Decoupling Representation"],"prefix":"10.1007","author":[{"given":"Zuohao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingsheng","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"30_CR2","unstructured":"Bertsekas, D.: Reinforcement Learning and Optimal Control, vol.\u00a01. Athena Scientific (2019)"},{"issue":"4","key":"30_CR3","doi-asserted-by":"publisher","first-page":"2443","DOI":"10.3390\/app13042443","volume":"13","author":"K Souchleris","year":"2023","unstructured":"Souchleris, K., Sidiropoulos, G.K., Papakostas, G.A.: Reinforcement learning in game industry\u2013review, prospects and challenges. Appl. Sci. 13(4), 2443 (2023)","journal-title":"Appl. Sci."},{"issue":"6","key":"30_CR4","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"B Ravi Kiran","year":"2021","unstructured":"Ravi Kiran, B., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"30_CR5","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1002\/widm.1124","volume":"4","author":"T Bartz-Beielstein","year":"2014","unstructured":"Bartz-Beielstein, T., Branke, J., Mehnen, J., Mersmann, O.: Evolutionary algorithms. Wiley Interdis. Rev. Data Min. Knowl. Discov. 4(3), 178\u2013195 (2014)","journal-title":"Wiley Interdis. Rev. Data Min. Knowl. Discov."},{"key":"30_CR6","doi-asserted-by":"publisher","first-page":"0025","DOI":"10.34133\/icomputing.0025","volume":"2","author":"H Bai","year":"2023","unstructured":"Bai, H., Cheng, R., Jin, Y.: Evolutionary reinforcement learning: a survey. Intell. Comput. 2, 0025 (2023)","journal-title":"Intell. Comput."},{"key":"30_CR7","unstructured":"Khadka, S., et al.: Collaborative evolutionary reinforcement learning. In International Conference on Machine Learning, pp. 3341\u20133350. PMLR (2019)"},{"key":"30_CR8","unstructured":"Khadka, S., Tumer., K.: Evolution-guided policy gradient in reinforcement learning. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"issue":"1","key":"30_CR9","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1145\/234313.234350","volume":"28","author":"S Forrest","year":"1996","unstructured":"Forrest, S.: Genetic algorithms. ACM Comput. Surv. (CSUR) 28(1), 77\u201380 (1996)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"30_CR10","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"30_CR11","unstructured":"Pourchot, A., Sigaud, O.: CEM-RL: combining evolutionary and gradient-based methods for policy search. arXiv preprint arXiv:1810.01222 (2018)"},{"key":"30_CR12","doi-asserted-by":"publisher","unstructured":"Ma, Y., Liu, T., Wei, B., Liu, Y., Xu, K., Li, W.: Evolutionary action selection for gradient-based policy learning. In: International Conference on Neural Information Processing, pp. 579\u2013590. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-30111-7_49","DOI":"10.1007\/978-3-031-30111-7_49"},{"key":"30_CR13","unstructured":"Zeng, Y., Cai, R., Sun, F., Huang, L., Hao, Z.: A survey on causal reinforcement learning (2023)"},{"issue":"3","key":"30_CR14","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G., et al.: Temporal difference learning and td-gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"key":"30_CR15","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":"30_CR16","doi-asserted-by":"publisher","unstructured":"B\u00e4ck, T., Schwefel, H.P.: Evolutionary Algorithms: Theory and Applications. Springer (1993). https:\/\/doi.org\/10.1007\/978-3-032-00385-0_27","DOI":"10.1007\/978-3-032-00385-0_27"},{"key":"30_CR17","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"PT De Boer","year":"2005","unstructured":"De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Opera. Res. 134, 19\u201367 (2005)","journal-title":"Ann. Opera. Res."},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Zheng, H., Jiang, J., Wei, P., Long, G., Zhang, C.: Competitive and cooperative heterogeneous deep reinforcement learning. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS (2020)","DOI":"10.65109\/HRYD1418"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Online meta-learning by parallel algorithm competition. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 426\u2013433 (2018)","DOI":"10.1145\/3205455.3205486"},{"key":"30_CR20","unstructured":"Franke, J.K.H., K\u00f6hler, G., Biedenkapp, A., Hutter, F.: Sample-efficient automated deep reinforcement learning. arXiv preprint arXiv:2009.01555 (2020)"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Bodnar, C., Day, B., Li\u00f3, P.: Proximal distilled evolutionary reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3283\u20133290 (2020)","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Pearl, J.: Causality. Cambridge university press (2009)","DOI":"10.1017\/CBO9780511803161"},{"key":"30_CR23","unstructured":"Chen, X., et al.: Variational lossy autoencoder. arXiv preprint arXiv:1611.02731 (2016)"},{"key":"30_CR24","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: International Conference on Machine Learning, pp. 2649\u20132658. PMLR (2018)"},{"key":"30_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, (2017)"},{"key":"30_CR26","unstructured":"Haarnoja, T., et\u00a0al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8405-5_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:20Z","timestamp":1775074520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8405-5_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584048","9789819584055"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8405-5_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}