{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:09:52Z","timestamp":1778364592945,"version":"3.51.4"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032191045","type":"print"},{"value":"9783032191052","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\/978-3-032-19105-2_3","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:03:57Z","timestamp":1778364237000},"page":"30-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["When Intrinsic Motivation Fails: Exploration Challenges in\u00a0Decentralized MARL"],"prefix":"10.1007","author":[{"given":"Ting","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Montana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"3_CR1","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"3_CR2","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"key":"3_CR3","unstructured":"De\u00a0Witt, C.S., Gupta, T., Makoviichuk, D., Makoviychuk, V., Torr, P.H., Sun, M., Whiteson, S.: Is independent learning all you need in the starcraft multi-agent challenge? arXiv preprint arXiv:2011.09533 (2020)"},{"key":"3_CR4","unstructured":"Henaff, M., Jiang, M., Raileanu, R.: A study of global and episodic bonuses for exploration in contextual mdps. In: International Conference on Machine Learning. pp. 12972\u201312999. PMLR (2023)"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"37631","DOI":"10.52202\/068431-2728","volume":"35","author":"M Henaff","year":"2022","unstructured":"Henaff, M., Raileanu, R., Jiang, M., Rockt\u00e4schel, T.: Exploration via elliptical episodic bonuses. Adv. Neural. Inf. Process. Syst. 35, 37631\u201337646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR6","unstructured":"Iqbal, S., Sha, F.: Coordinated exploration via intrinsic rewards for multi-agent reinforcement learning. arXiv preprint arXiv:1905.12127 (2019)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, H., Ding, Z., Lu, Z.: Settling decentralized multi-agent coordinated exploration by novelty sharing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 17444\u201317452 (2024)","DOI":"10.1609\/aaai.v38i16.29693"},{"key":"3_CR8","doi-asserted-by":"publisher","first-page":"20469","DOI":"10.52202\/068431-1488","volume":"35","author":"J Jiang","year":"2022","unstructured":"Jiang, J., Lu, Z.: I2q: a fully decentralized q-learning algorithm. Adv. Neural. Inf. Process. Syst. 35, 20469\u201320481 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR9","first-page":"15230","volume":"34","author":"T Lin","year":"2021","unstructured":"Lin, T., Huh, J., Stauffer, C., Lim, S.N., Isola, P.: Learning to ground multi-agent communication with autoencoders. Adv. Neural. Inf. Process. Syst. 34, 15230\u201315242 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR10","unstructured":"Liu, B., Pu, Z., Pan, Y., Yi, J., Liang, Y., Zhang, D.: Lazy agents: a new perspective on solving sparse reward problem in multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 21937\u201321950. PMLR (2023)"},{"key":"3_CR11","unstructured":"Lo, Y.L., Sengupta, B., Foerster, J., Noukhovitch, M.: Learning multi-agent communication with contrastive learning. arXiv preprint arXiv:2307.01403 (2023)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International conference on machine learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Toquebiau, M., Bredeche, N., Benamar, F., Jun, J.Y.: Joint intrinsic motivation for coordinated exploration in multi-agent deep reinforcement learning. arXiv preprint arXiv:2402.03972 (2024)","DOI":"10.65109\/IUHQ8304"},{"issue":"1","key":"3_CR14","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TCCN.2020.3027695","volume":"7","author":"L Wang","year":"2020","unstructured":"Wang, L., Wang, K., Pan, C., Xu, W., Aslam, N., Hanzo, L.: Multi-agent deep reinforcement learning-based trajectory planning for multi-UAV assisted mobile edge computing. IEEE Trans. Cogn. Commun. Netw. 7(1), 73\u201384 (2020)","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"3_CR15","unstructured":"Wang, T., Wang, J., Wu, Y., Zhang, C.: Influence-based multi-agent exploration. arXiv preprint arXiv:1910.05512 (2019)"},{"key":"3_CR16","first-page":"10053","volume":"33","author":"J Xu","year":"2020","unstructured":"Xu, J., Zhong, F., Wang, Y.: Learning multi-agent coordination for enhancing target coverage in directional sensor networks. Adv. Neural. Inf. Process. Syst. 33, 10053\u201310064 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR17","first-page":"25217","volume":"34","author":"T Zhang","year":"2021","unstructured":"Zhang, T., et al.: Noveld: a simple yet effective exploration criterion. Adv. Neural. Inf. Process. Syst. 34, 25217\u201325230 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR18","first-page":"3757","volume":"34","author":"L Zheng","year":"2021","unstructured":"Zheng, L., et al.: Episodic multi-agent reinforcement learning with curiosity-driven exploration. Adv. Neural. Inf. Process. Syst. 34, 3757\u20133769 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Zhou, M., Ma, X., Li, Y.: A novel multi-objective routing scheme based on cooperative multi-agent reinforcement learning for metaverse services in fixed 6g. In: WOCN (2023). https:\/\/dblp.org\/rec\/conf\/wocc\/ZhouML23, https:\/\/doi.org\/10.1109\/WOCC52294.2023.00029","DOI":"10.1109\/WOCC52294.2023.00029"},{"key":"3_CR20","unstructured":"Zhu, T., Jin, Y., Houssineau, J., Montana, G.: Mitigating relative over-generalization in multi-agent reinforcement learning. arXiv preprint arXiv:2411.11099 (2024)"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19105-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:04:01Z","timestamp":1778364241000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19105-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032191045","9783032191052"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19105-2_3","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}