{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:59:17Z","timestamp":1774663157566,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":51,"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_5","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T19:56:32Z","timestamp":1753473392000},"page":"51-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-agent Reinforcement Learning via Co-Evolutionary Task Evolution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0941-3316","authenticated-orcid":false,"given":"Yufei","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2593-3621","authenticated-orcid":false,"given":"Chengwei","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3051-5642","authenticated-orcid":false,"given":"Huanzhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8392-4148","authenticated-orcid":false,"given":"Kangsheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2901-6193","authenticated-orcid":false,"given":"Linuo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7641-2623","authenticated-orcid":false,"given":"Shuyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","first-page":"20200364","DOI":"10.1098\/rsta.2020.0364","volume":"379","author":"H Abbass","year":"2021","unstructured":"Abbass, H., Petraki, E., Hussein, A., McCall, F., Elsawah, S.: A model of symbiomemesis: machine education and communication as pillars for human-autonomy symbiosis. Phil. Trans. R. Soc. A 379, 20200364 (2021)","journal-title":"Phil. Trans. R. Soc. A"},{"key":"5_CR2","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s13042-020-01167-7","volume":"12","author":"A Perrusqu\u00eda","year":"2021","unstructured":"Perrusqu\u00eda, A., Yu, W., Li, X.: Multi-agent reinforcement learning for redundant robot control in task-space. Int. J. Mach. Learn. Cybern. 12, 231\u2013241 (2021)","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"5_CR3","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., et al.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21, 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR4","unstructured":"Shalev-Shwartz, S., Shammah, S., Shashua, A.: Safe, multi-agent, reinforcement learning for autonomous driving. arXiv preprint arXiv:1610.03295 (2016)"},{"key":"5_CR5","first-page":"278","volume":"99","author":"AY Ng","year":"1999","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In Icml 99, 278\u2013287 (1999)","journal-title":"In Icml"},{"key":"5_CR6","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":"5_CR7","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 627\u2013635. JMLR Workshop and Conference Proceedings (2011)"},{"key":"5_CR8","unstructured":"Duan, Y., et al.: One-shot imitation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR9","unstructured":"Florensa, C., Held, D., Wulfmeier, M., Zhang, M., Abbeel, P.: Reverse curriculum generation for reinforcement learning. In: Conference on Robot Learning, pp. 482\u2013495. PMLR (2017)"},{"key":"5_CR10","unstructured":"Florensa, C., Held, D., Geng, X., Abbeel, P.: Automatic goal generation for reinforcement learning agents. In: International Conference on Machine Learning, pp. 1515\u20131528. PMLR (2018)"},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1613\/jair.4818","volume":"53","author":"D Bloembergen","year":"2015","unstructured":"Bloembergen, D., Tuyls, K., Hennes, D., Kaisers, M.: Evolutionary dynamics of multi-agent learning: a survey. J. Artif. Intell. Res. 53, 659\u2013697 (2015)","journal-title":"J. Artif. Intell. Res."},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Bu\u00b8soniu, L., Babu\u0161ka, R., De Schutter, B.: Multi-agent reinforcement learning: an overview. Innov. Multi-agent Syst. Appl. 1, 183\u2013221 (2010)","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","volume":"33","author":"P Hernandez-Leal","year":"2019","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: A survey and critique of multiagent deep reinforcement learning. Auton. Agents Multi-Agent Syst. 33, 750\u2013797 (2019)","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"5_CR14","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/TEVC.2017.2767023","volume":"22","author":"LM Antonio","year":"2017","unstructured":"Antonio, L.M., Coello, C.A.C.: Coevolutionary multiobjective evolutionary algorithms: survey of the state-of-the-art. IEEE Trans. Evol. Comput. 22, 851\u2013865 (2017)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"5_CR15","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":"5_CR16","unstructured":"Dewey, D.: Reinforcement learning and the reward engineering principle. In: 2014 AAAI Spring Symposium Series, vol. 9, no. 11 (2014)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Booth, S., et al.: The perils of trial-and-error reward design: misdesign through overfitting and invalid task specifications. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 5920\u20135929 (2023)","DOI":"10.1609\/aaai.v37i5.25733"},{"key":"5_CR18","unstructured":"Laud, A.D.: Theory and application of reward shaping in reinforcement learning. University of Illinois at Urbana Champaign (2004)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Barto, A.G.: Intrinsic motivation and reinforcement learning. In: Intrinsically Motivated Learning Natural Artificial Systems, pp. 17\u201347 (2013)","DOI":"10.1007\/978-3-642-32375-1_2"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41\u201348 (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/S0010-0277(99)00031-1","volume":"72","author":"DL Rohde","year":"1999","unstructured":"Rohde, D.L., Plaut, D.C.: Language acquisition in the absence of explicit negative evidence: how important is starting small? Cognition 72, 67\u2013109 (1999)","journal-title":"Cognition"},{"key":"5_CR22","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","volume":"48","author":"JL Elman","year":"1993","unstructured":"Elman, J.L.: Learning and development in neural networks: the importance of starting small. Cognition 48, 71\u201399 (1993)","journal-title":"Cognition"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Narvekar, S., Sinapov, J., Stone, P.: Autonomous task sequencing for customized curriculum design in reinforcement learning. In: IJCAI, pp. 2536\u20132542 (2017)","DOI":"10.24963\/ijcai.2017\/353"},{"key":"5_CR24","unstructured":"Wang, R., Lehman, J., Clune, J., Stanley, K.O.: Paired open-ended trailblazer (poet): endlessly generating increasingly complex and diverse learning environments and their solutions. arXiv preprint arXiv:1901.01753 (2019)"},{"key":"5_CR25","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. In: International Conference on Machine Learning, pp. 1282\u20131289. PMLR (2019)"},{"key":"5_CR26","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.1109\/TNNLS.2018.2790981","volume":"29","author":"Z Ren","year":"2018","unstructured":"Ren, Z., Dong, D., Li, H., Chen, C.: Self-paced prioritized curriculum learning with coverage penalty in deep reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 29, 2216\u20132226 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Portal: Automatic curricula generation for multiagent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 15934\u201315942 (2024)","DOI":"10.1609\/aaai.v38i14.29524"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, X., Guo, Z., Hu, T., Ma, H.: Csce: boosting llm reasoning by simultaneous enhancing of casual significance and consistency. arXiv preprint arXiv:2409.17174 (2024)","DOI":"10.21203\/rs.3.rs-6224619\/v1"},{"key":"5_CR29","unstructured":"Samvelyan, M., et al.: Maestro: Open-ended environment design for multi-agent reinforcement learning. arXiv preprint arXiv:2303.03376 (2023)"},{"key":"5_CR30","unstructured":"Parker-Holder, J., et al.: Evolving curricula with regret-based environment design. In: International Conference on Machine Learning, pp. 17473\u201317498. PMLR (2022)"},{"key":"5_CR31","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1023\/A:1015059928466","volume":"1","author":"H-G Beyer","year":"2002","unstructured":"Beyer, H.-G., Schwefel, H.-P.: Evolution strategies\u2013a comprehensive introduction. Nat. Comput. 1, 3\u201352 (2002)","journal-title":"Nat. Comput."},{"key":"5_CR32","unstructured":"Miconi, T., Rawal, A., Clune, J., Stanley, K.O.\u201d Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity. arXiv preprint arXiv:2002.10585 (2020)"},{"key":"5_CR33","doi-asserted-by":"publisher","first-page":"98","DOI":"10.3389\/frobt.2020.00098","volume":"7","author":"P Pagliuca","year":"2020","unstructured":"Pagliuca, P., Milano, N., Nolfi, S.: Efficacy of modern neuro-evolutionary strategies for continuous control optimization. Front. Rob. AI 7, 98 (2020)","journal-title":"Front. Rob. AI"},{"key":"5_CR34","unstructured":"Long, Q., et al.: Evolutionary population curriculum for scaling multi-agent reinforcement learning. arXiv preprint arXiv:2003.10423 (2020)"},{"key":"5_CR35","first-page":"24611","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu, C., et al.: The surprising effectiveness of ppo in cooperative multi-agent games. Adv. Neural. Inf. Process. Syst. 35, 24611\u201324624 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Song, Y., Schneider, J.: Robust reinforcement learning via genetic curriculum. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 5560\u20135566 IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812420"},{"key":"5_CR37","unstructured":"Racaniere, S., et al.: Automated curricula through setter-solver interactions. arXiv preprint arXiv:1909.12892 (2019)"},{"key":"5_CR38","unstructured":"Cahill, A.: Catastrophic forgetting in reinforcement-learning environments. Ph.D. thesis. Citeseer (2011)"},{"key":"5_CR39","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","volume":"3","author":"RM French","year":"1999","unstructured":"French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128\u2013135 (1999)","journal-title":"Trends Cogn. Sci."},{"key":"5_CR40","unstructured":"Lowe, R., et al.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR41","unstructured":"Baker, B., et al.: Emergent tool use from multi-agent autocurricula. arXiv preprint arXiv:1909.07528 (2019)"},{"key":"5_CR42","first-page":"261","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 261\u2013272 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"5_CR43","first-page":"9681","volume":"34","author":"J Chen","year":"2021","unstructured":"Chen, J., et al.: Variational automatic curriculum learning for sparse-reward cooperative multi-agent problems. Adv. Neural. Inf. Process. Syst. 34, 9681\u20139693 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Qi, X., Zhang, Z., Zheng, H., et al.: MedConv: convolutions beat transformers on long-tailed bone density prediction. arXiv preprint arXiv:2502.00631 (2025)","DOI":"10.1109\/IJCNN64981.2025.11227632"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, X., Guo, Z., et al.: CSCE: boosting LLM reasoning by simultaneous enhancing of causal significance and consistency. arXiv preprint arXiv:2409.17174 (2024)","DOI":"10.21203\/rs.3.rs-6224619\/v1"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Liu, S., Wang, K.: Comprehensive review: advancing cognitive computing through theory of mind integration and deep learning in artificial intelligence. In: Proceedings of 8th International Conference on Computer Science and Application Engineering, pp. 31\u201335 (2024)","DOI":"10.1145\/3704814.3704822"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, K., Hu, T., et al.: Enhancing autonomous driving through dual-process learning with behavior and reflection integration. In: ICASSP 2025 \u2013 IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp. 1\u20135. IEEE, Seoul (2025)","DOI":"10.1109\/ICASSP49660.2025.10889717"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Zou, B., Guo, Z., Qin, W., et al.: Synergistic spotting and recognition of micro-expression via temporal state transition. In: ICASSP 2025 \u2013 IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp. 1\u20135. IEEE, Seoul (2025)","DOI":"10.1109\/ICASSP49660.2025.10888508"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Hu, T., Zhang, X., Ma, H., et al.: Autonomous driving system based on dual process theory and deliberate practice theory (2025)","DOI":"10.21203\/rs.3.rs-5746545\/v1"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, K., Hu, T., et al.: Efficient knowledge transfer in multi-task learning through task-adaptive low-rank representation. arXiv preprint arXiv:2505.00009 (2025)","DOI":"10.21203\/rs.3.rs-6487493\/v1"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Wang, K., Ye, C., Zhang, H., et al.: Graph-driven multimodal feature learning framework for apparent personality assessment. arXiv preprint arXiv:2504.11515 (2025)","DOI":"10.21203\/rs.3.rs-6455809\/v1"}],"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_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:36:13Z","timestamp":1774661773000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9894-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698936","9789819698943"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9894-3_5","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"}}]}}