{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:56:33Z","timestamp":1777654593621,"version":"3.51.4"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731129","type":"print"},{"value":"9783031731136","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73113-6_1","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:45:18Z","timestamp":1732092318000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement Learning Friendly Vision-Language Model for\u00a0Minecraft"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7114-534X","authenticated-orcid":false,"given":"Haobin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junpeng","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4612-5450","authenticated-orcid":false,"given":"Hao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziluo","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3967-2704","authenticated-orcid":false,"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"1_CR2","unstructured":"Baker, B., et al.: Video pretraining (VPT): learning to act by watching unlabeled online videos. arXiv preprint arXiv:2206.11795 (2022)"},{"key":"1_CR3","unstructured":"Baumli, K., et\u00a0al.: Vision-language models as a source of rewards. arXiv preprint arXiv:2312.09187 (2023)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cai, S., Wang, Z., Ma, X., Liu, A., Liang, Y.: Open-world multi-task control through goal-aware representation learning and adaptive horizon prediction. arXiv preprint arXiv:2301.10034 (2023)","DOI":"10.1109\/CVPR52729.2023.01320"},{"key":"1_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Dzabraev, M., Kalashnikov, M., Komkov, S., Petiushko, A.: MDMMT: multidomain multimodal transformer for video retrieval. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2021)","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"1_CR8","unstructured":"Fan, L., et al.: MineDojo: building open-ended embodied agents with internet-scale knowledge. In: Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track (2022)"},{"key":"1_CR9","unstructured":"Guhr, O., Schumann, A.K., Bahrmann, F., B\u00f6hme, H.J.: Fullstop: multilingual deep models for punctuation prediction, June 2021. http:\/\/ceur-ws.org\/Vol-2957\/sepp_paper4.pdf"},{"key":"1_CR10","unstructured":"Guss, W.H., et\u00a0al.: NeurIPS 2019 competition: the MineRL competition on sample efficient reinforcement learning using human priors. arXiv preprint arXiv:1904.10079 (2019)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Guss, W.H., et al.: MineRL: a large-scale dataset of minecraft demonstrations. In: International Joint Conference on Artificial Intelligence (IJCAI) (2019)","DOI":"10.24963\/ijcai.2019\/339"},{"key":"1_CR12","unstructured":"Hafner, D., Pasukonis, J., Ba, J., Lillicrap, T.P.: Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104 (2023)"},{"key":"1_CR13","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s10115-006-0053-3","volume":"14","author":"N Haiminen","year":"2008","unstructured":"Haiminen, N., Gionis, A., Laasonen, K.: Algorithms for unimodal segmentation with applications to unimodality detection. Knowl. Inf. Syst. 14, 39\u201357 (2008)","journal-title":"Knowl. Inf. Syst."},{"key":"1_CR14","unstructured":"Johnson, M., Hofmann, K., Hutton, T., Bignell, D.: The Malmo platform for artificial intelligence experimentation. In: International Joint Conference on Artificial Intelligence (IJCAI) (2016)"},{"issue":"1\u20132","key":"1_CR15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"key":"1_CR16","unstructured":"Kanervisto, A., et al.: MineRL diamond 2021 competition: overview, results, and lessons learned. arXiv preprint arXiv:2202.10583 (2022)"},{"key":"1_CR17","unstructured":"Li, Y., Wang, H., Duan, Y., Li, X.: Clip surgery for better explainability with enhancement in open-vocabulary tasks. arXiv preprint arXiv:2304.05653 (2023)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Lin, Z., Li, J., Shi, J., Ye, D., Fu, Q., Yang, W.: JueWu-MC: playing minecraft with sample-efficient hierarchical reinforcement learning. arXiv preprint arXiv:2112.04907 (2021)","DOI":"10.24963\/ijcai.2022\/452"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: Hit: hierarchical transformer with momentum contrast for video-text retrieval. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"1_CR20","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4clip: an empirical study of CLIP for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"1_CR21","unstructured":"Ma, Y.J., et al.: Eureka: Human-level reward design via coding large language models. arXiv preprint arXiv:2310.12931 (2023)"},{"key":"1_CR22","unstructured":"Nottingham, K., et al.: Do embodied agents dream of pixelated sheep?: Embodied decision making using language guided world modelling. arXiv preprint arXiv:2301.12050 (2023)"},{"key":"1_CR23","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"1_CR24","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"1_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, ICML (2021)"},{"key":"1_CR26","doi-asserted-by":"publisher","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.04356, https:\/\/arxiv.org\/abs\/2212.04356","DOI":"10.48550\/ARXIV.2212.04356"},{"key":"1_CR27","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"1_CR28","unstructured":"Shah, R., et al.: Retrospective on the 2021 mineRL BASALT competition on learning from human feedback. In: Neural Information Processing Systems (NeurIPS) Competitions and Demonstrations Track (2021)"},{"key":"1_CR29","unstructured":"Shu, T., Xiong, C., Socher, R.: Hierarchical and interpretable skill acquisition in multi-task reinforcement learning. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Tessler, C., Givony, S., Zahavy, T., Mankowitz, D., Mannor, S.: A deep hierarchical approach to lifelong learning in minecraft. In: AAAI Conference on Artificial Intelligence (AAAI) (2017)","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"1_CR31","unstructured":"Wang, G., et al.: Voyager: an open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023)"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Videoclip: contrastive pre-training for zero-shot video-text understanding. arXiv preprint arXiv:2109.14084 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"1_CR33","unstructured":"Yuan, H., et al.: Plan4MC: skill reinforcement learning and planning for open-world minecraft tasks. arXiv preprint arXiv:2303.16563 (2023)"},{"key":"1_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-031-19815-1_40","volume-title":"ECCV 2022","author":"C Zhou","year":"2022","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40"},{"key":"1_CR35","unstructured":"Zhu, X., et\u00a0al.: Ghost in the minecraft: generally capable agents for open-world environments via large language models with text-based knowledge and memory. arXiv preprint arXiv:2305.17144 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73113-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:05:28Z","timestamp":1732097128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73113-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031731129","9783031731136"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73113-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}