{"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":1788728976744,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":36,"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_15","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:43:19Z","timestamp":1788727399000},"page":"255-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the\u00a0Offline-to-Online Gap in\u00a0Cooperative Behavior Cloning with\u00a0Distilled Intent Modeling"],"prefix":"10.1007","author":[{"given":"Haoxi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Rong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"15_CR1","unstructured":"Abel, D., Arumugam, D., Lehnert, L., Littman, M.: State abstractions for lifelong reinforcement learning. In: International Conference on Machine Learning, pp. 10\u201319. PMLR (2018)"},{"key":"15_CR2","unstructured":"Allen, C., Parikh, N., Gottesman, O., Konidaris, G.: Learning markov state abstractions for deep reinforcement learning. Adv. Neural Inf. Process. Syst. 34, 8229\u20138241 (2021)"},{"key":"15_CR3","unstructured":"Andreas, J., Klein, D., Levine, S.: Modular multitask reinforcement learning with policy sketches. In: International Conference on Machine Learning, pp. 166\u2013175. PMLR (2017)"},{"key":"15_CR4","unstructured":"Carroll, M., et al.: On the utility of learning about humans for human-ai coordination. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"15_CR5","unstructured":"Charakorn, R., Manoonpong, P., Dilokthanakul, N.: Generating diverse cooperative agents by learning incompatible policies. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Chatterjee, A., Renduchintala, H.K., Bhatia, S., Chakraborty, T.: Posix: a prompt sensitivity index for large language models. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 14550\u201314565 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.852"},{"key":"15_CR7","unstructured":"Witt, D., et al.: Is independent learning all you need in the starcraft multi-agent challenge? arXiv preprint (2020). arXiv:2011.09533"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Delfosse, Q., Sztwiertnia, S., Rothermel, M., Stammer, W., Kersting, K.: Interpretable concept bottlenecks to align reinforcement learning agents. Adv. Neural Inf. Process. Syst. 37, 66826\u201366855 (2024)","DOI":"10.52202\/079017-2135"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Garg, D., Vaidyanath, S., Kim, K., Song, J., Ermon, S.: Lisa: learning interpretable skill abstractions from language. Adv. Neural Inf. Process. Syst. 35, 21711\u201321724 (2022)","DOI":"10.52202\/068431-1578"},{"key":"15_CR10","unstructured":"Gessler, T., Dizdarevic, T., Calinescu, A., Ellis, B., Lupu, A., Foerster, J.N.: OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination (2025). arXiv preprint arXiv:2503.17821"},{"key":"15_CR11","unstructured":"Hansen, E.A., Bernstein, D.S., Zilberstein, S.: Dynamic programming for partially observable stochastic games. In: AAAI, vol. 4, pp. 709\u2013715 (2004)"},{"key":"15_CR12","unstructured":"Hausman, K., Chebotar, Y., Schaal, S., Sukhatme, G., Lim, J.J.: Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"15_CR13","unstructured":"He, H., Boyd-Graber, J., Kwok, K., Daum\u00e9, I., H.: Opponent modeling in deep reinforcement learning. In: International Conference on Machine Learning, pp. 1804\u20131813. PMLR (2016)"},{"issue":"2","key":"15_CR14","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. Iclr 1(2), 3 (2022)","journal-title":"Iclr"},{"key":"15_CR15","unstructured":"Hu, H., Lerer, A., Peysakhovich, A., Foerster, J.: \u201cOther-play\u201d for zero-shot coordination. In: International Conference on Machine Learning, pp. 4399\u20134410. PMLR (2020)"},{"key":"15_CR16","unstructured":"Hu, H., Sadigh, D.: Language instructed reinforcement learning for human-ai coordination. In: International Conference on Machine Learning, pp. 13584\u201313598. PMLR (2023)"},{"key":"15_CR17","unstructured":"Jaderberg, M., et al.: Population based training of neural networks (2017). arXiv preprint arXiv:1711.09846"},{"key":"15_CR18","unstructured":"Jiang, Y., Gu, S.S., Murphy, K.P., Finn, C.: Language as an abstraction for hierarchical deep reinforcement learning. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"15_CR19","unstructured":"Koh, P.W., et al.: Concept bottleneck models. In: International Conference on Machine Learning, pp. 5338\u20135348. PMLR (2020)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Liang, Y., Chen, D., Gupta, A., Du, S.S., Jaques, N.: Learning to cooperate with humans using generative agents. Adv. Neural Inf. Process. Syst. 37, 60061\u201360087 (2024)","DOI":"10.52202\/079017-1918"},{"key":"15_CR21","unstructured":"Liu, A., et\u00a0al.: Deepseek-v3. 2: pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556 (2025)"},{"key":"15_CR22","unstructured":"Liu, J., et al.: Llm-powered hierarchical language agent for real-time human-ai coordination (2023). arXiv preprint arXiv:2312.15224"},{"key":"15_CR23","unstructured":"Luketina, J., et al.: A survey of reinforcement learning informed by natural language (2019). arXiv preprint arXiv:1906.03926"},{"key":"15_CR24","unstructured":"Papoudakis, G., Albrecht, S.V.: Variational autoencoders for opponent modeling in multi-agent systems (2020). arXiv preprint arXiv:2001.10829"},{"key":"15_CR25","unstructured":"Papoudakis, G., Christianos, F., Albrecht, S.: Agent modelling under partial observability for deep reinforcement learning. Adv. Neural Inf. Process. Syst. 34, 19210\u201319222 (2021)"},{"key":"15_CR26","unstructured":"Rahman, M.A., Hopner, N., Christianos, F., Albrecht, S.V.: Towards open ad hoc teamwork using graph-based policy learning. In: International Conference on Machine Learning, pp. 8776\u20138786. PMLR(2021)"},{"key":"15_CR27","unstructured":"Ross, S., Bagnell, D.: Efficient reductions for imitation learning. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 661\u2013668. JMLR Workshop and Conference Proceedings (2010)"},{"key":"15_CR28","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":"15_CR29","unstructured":"Strouse, D., McKee, K., Botvinick, M., Hughes, E., Everett, R.: Collaborating with humans without human data. Adv. Neural Inf. Process. Syst. 34, 14502\u201314515 (2021)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Tang, J., Swamy, G., Fang, F., Wu, Z.S.: Multi-agent imitation learning: value is easy, regret is hard. Adv. Neural Inf. Process. Syst. 37, 27790\u201327816 (2024)","DOI":"10.52202\/079017-0872"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Z., Wen, Y., Gong, Z., Punakkath, F., Zou, S., Wang, J.: A regularized opponent model with maximum entropy objective (2019). arXiv preprint arXiv:1905.08087","DOI":"10.24963\/ijcai.2019\/85"},{"key":"15_CR32","unstructured":"Wang, Y., Zhong, F., Xu, J., Wang, Y.: Tom2c: target-oriented multi-agent communication and cooperation with theory of mind. arXiv preprint arXiv:2111.09189 (2021)"},{"key":"15_CR33","unstructured":"Wen, Y., Yang, Y., Luo, R., Wang, J., Pan, W.: Probabilistic recursive reasoning for multi-agent reinforcement learning (2019). arXiv preprint arXiv:1901.09207"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Yan, X., Guo, J., Lou, X., Wang, J., Zhang, H., Du, Y.: An efficient end-to-end training approach for zero-shot human-ai coordination. Adv. Neural Inf. Process. Syst. 36, 2636\u20132658 (2023)","DOI":"10.52202\/075280-0119"},{"key":"15_CR35","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Yu, X., Jiang, J., Lu, Z.: Opponent modeling based on subgoal inference. Adv. Neural Inf. Process. Syst. 37, 60531\u201360555 (2024)","DOI":"10.52202\/079017-1936"}],"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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:43:23Z","timestamp":1788727403000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37670-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"ISBN":["9783032376695","9783032376701"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37670-1_15","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":"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"}}]}}