{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:51:57Z","timestamp":1742914317794,"version":"3.40.3"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031728969"},{"type":"electronic","value":"9783031728976"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-72897-6_6","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:16:52Z","timestamp":1733095012000},"page":"88-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MaxMI: A Maximal Mutual Information Criterion for\u00a0Manipulation Concept Discovery"],"prefix":"10.1007","author":[{"given":"Pei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanchao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"6_CR1","unstructured":"Ajay, A., Du, Y., Gupta, A., Tenenbaum, J.B., Jaakkola, T.S., Agrawal, P.: Is conditional generative modeling all you need for decision making? In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"issue":"5","key":"6_CR2","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469\u2013483 (2009)","journal-title":"Robot. Auton. Syst."},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a031 (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"6_CR4","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"6_CR5","unstructured":"Brohan, A., et\u00a0al.: RT-1: robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022)"},{"key":"6_CR6","unstructured":"Brohan, A., et\u00a0al.: Do as i can, not as i say: grounding language in robotic affordances. In: Conference on Robot Learning, pp. 287\u2013318. PMLR (2023)"},{"key":"6_CR7","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. Adv. Neural. Inf. Process. Syst. 34, 15084\u201315097 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Arkin, J., Zhang, Y., Roy, N., Fan, C.: Autotamp: autoregressive task and motion planning with LLMs as translators and checkers. arXiv preprint arXiv:2306.06531 (2023)","DOI":"10.1109\/ICRA57147.2024.10611163"},{"key":"6_CR9","unstructured":"Di\u00a0Palo, N., Byravan, A., Hasenclever, L., Wulfmeier, M., Heess, N., Riedmiller, M.: Towards a unified agent with foundation models. In: Workshop on Reincarnating Reinforcement Learning at ICLR 2023 (2023)"},{"key":"6_CR10","unstructured":"Driess, D., et\u00a0al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"issue":"2\u20133","key":"6_CR11","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1177\/0278364919872545","volume":"39","author":"K Fang","year":"2020","unstructured":"Fang, K., et al.: Learning task-oriented grasping for tool manipulation from simulated self-supervision. Int. J. Robot. Res. 39(2\u20133), 202\u2013216 (2020)","journal-title":"Int. J. Robot. Res."},{"key":"6_CR12","unstructured":"Finn, C., Levine, S., Abbeel, P.: Guided cost learning: Deep inverse optimal control via policy optimization. In: International Conference on Machine Learning, pp. 49\u201358. PMLR (2016)"},{"key":"6_CR13","unstructured":"Firoozi, R., et\u00a0al.: Foundation models in robotics: applications, challenges, and the future. arXiv preprint arXiv:2312.07843 (2023)"},{"key":"6_CR14","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4RL: datasets for deep data-driven reinforcement learning (2020)"},{"key":"6_CR15","unstructured":"Gu, J., et al.: Maniskill2: a unified benchmark for generalizable manipulation skills. In: International Conference on Learning Representations (2023)"},{"key":"6_CR16","unstructured":"Gupta, A., Kumar, V., Lynch, C., Levine, S., Hausman, K.: Relay policy learning: solving long-horizon tasks via imitation and reinforcement learning. arXiv preprint arXiv:1910.11956 (2019)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14953\u201314962 (2023)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"6_CR18","unstructured":"von Hartz, J.O., Chisari, E., Welschehold, T., Valada, A.: Self-supervised learning of multi-object keypoints for robotic manipulation. arXiv preprint arXiv:2205.08316 (2022)"},{"key":"6_CR19","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"6_CR20","unstructured":"Hu, Z., Kang, S., Zeng, Q., Huang, K., Yang, Y.: Infonet: neural estimation of mutual information without test-time optimization. arXiv preprint arXiv:2402.10158 (2024)"},{"key":"6_CR21","unstructured":"Huang, S., Jiang, Z., Dong, H., Qiao, Y., Gao, P., Li, H.: Instruct2act: mapping multi-modality instructions to robotic actions with large language model. arXiv preprint arXiv:2305.11176 (2023)"},{"key":"6_CR22","unstructured":"Huang, W., Wang, C., Zhang, R., Li, Y., Wu, J., Fei-Fei, L.: Voxposer: composable 3D value maps for robotic manipulation with language models. arXiv preprint arXiv:2307.05973 (2023)"},{"issue":"1","key":"6_CR23","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3390\/make4010009","volume":"4","author":"M Hutsebaut-Buysse","year":"2022","unstructured":"Hutsebaut-Buysse, M., Mets, K., Latr\u00e9, S.: Hierarchical reinforcement learning: a survey and open research challenges. Mach. Learn. Knowl. Extr. 4(1), 172\u2013221 (2022)","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"6_CR24","unstructured":"Jia, Z., Liu, F., Thumuluri, V., Chen, L., Huang, Z., Su, H.: Chain-of-thought predictive control. arXiv preprint arXiv:2304.00776 (2023)"},{"key":"6_CR25","unstructured":"Kipf, T., et al.: Compile: compositional imitation learning and execution. In: International Conference on Machine Learning, pp. 3418\u20133428. PMLR (2019)"},{"issue":"3","key":"6_CR26","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1177\/0278364911428653","volume":"31","author":"G Konidaris","year":"2012","unstructured":"Konidaris, G., Kuindersma, S., Grupen, R., Barto, A.: Robot learning from demonstration by constructing skill trees. Int. J. Robot. Res. 31(3), 360\u2013375 (2012)","journal-title":"Int. J. Robot. Res."},{"key":"6_CR27","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"6_CR28","unstructured":"Laskey, M., Lee, J., Fox, R., Dragan, A., Goldberg, K.: Dart: noise injection for robust imitation learning. In: Conference on Robot Learning, pp. 143\u2013156. PMLR (2017)"},{"key":"6_CR29","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"6_CR30","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"6_CR32","first-page":"12608","volume":"35","author":"F Liu","year":"2022","unstructured":"Liu, F., Liu, H., Grover, A., Abbeel, P.: Masked autoencoding for scalable and generalizable decision making. Adv. Neural. Inf. Process. Syst. 35, 12608\u201312618 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR33","unstructured":"Liu, R., Luo, Q., Yang, Y.: Infocon: concept discovery with generative and discriminative informativeness. arXiv preprint arXiv:2404.10606 (2024)"},{"key":"6_CR34","unstructured":"Liu, Z., et\u00a0al.: Internchat: solving vision-centric tasks by interacting with chatbots beyond language. arXiv preprint arXiv:2305.05662 (2023)"},{"key":"6_CR35","unstructured":"Nair, A.V., Pong, V., Dalal, M., Bahl, S., Lin, S., Levine, S.: Visual reinforcement learning with imagined goals. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"6_CR36","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"6_CR37","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR38","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1146\/annurev-control-100819-063206","volume":"3","author":"H Ravichandar","year":"2020","unstructured":"Ravichandar, H., Polydoros, A.S., Chernova, S., Billard, A.: Recent advances in robot learning from demonstration. Ann. Rev. Control Robot. Auton. Syst. 3, 297\u2013330 (2020)","journal-title":"Ann. Rev. Control Robot. Auton. Syst."},{"key":"6_CR39","unstructured":"Riedmiller, M., et al.: Learning by playing solving sparse reward tasks from scratch. In: International Conference on Machine Learning, pp. 4344\u20134353. PMLR (2018)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Sasaki, F., Yamashina, R.: Behavioral cloning from noisy demonstrations. In: International Conference on Learning Representations (2020)","DOI":"10.1299\/jsmermd.2020.2A1-L11"},{"key":"6_CR41","unstructured":"Schaal, S.: Learning from demonstration. In: Advances in Neural Information Processing Systems, vol. 9 (1996)"},{"key":"6_CR42","first-page":"22955","volume":"35","author":"NM Shafiullah","year":"2022","unstructured":"Shafiullah, N.M., Cui, Z., Altanzaya, A.A., Pinto, L.: Behavior transformers: Cloning $$ k $$ modes with one stone. Adv. Neural. Inf. Process. Syst. 35, 22955\u201322968 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR43","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: solving AI tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580 (2023)"},{"key":"6_CR44","unstructured":"Shi, L.X., Sharma, A., Zhao, T.Z., Finn, C.: Waypoint-based imitation learning for robotic manipulation. In: Conference on Robot Learning (2023)"},{"key":"6_CR45","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning, pp. 785\u2013799. PMLR (2023)"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"6_CR47","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/3-540-45622-8_16","volume-title":"Abstraction, Reformulation, and Approximation","author":"M Stolle","year":"2002","unstructured":"Stolle, M., Precup, D.: Learning options in reinforcement learning. In: Koenig, S., Holte, R.C. (eds.) SARA 2002. LNCS (LNAI), vol. 2371, pp. 212\u2013223. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45622-8_16"},{"key":"6_CR48","unstructured":"Stooke, A., Lee, K., Abbeel, P., Laskin, M.: Decoupling representation learning from reinforcement learning. In: International Conference on Machine Learning, pp. 9870\u20139879. PMLR (2021)"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: Vipergpt: visual inference via python execution for reasoning. arXiv preprint arXiv:2303.08128 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"issue":"1\u20132","key":"6_CR50","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"6_CR51","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)"},{"key":"6_CR52","unstructured":"Wang, Y.J., Zhang, B., Chen, J., Sreenath, K.: Prompt a robot to walk with large language models. arXiv preprint arXiv:2309.09969 (2023)"},{"key":"6_CR53","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR54","unstructured":"Weng, Y., Mo, K., Shi, R., Yang, Y., Guibas, L.: Towards learning geometric eigen-lengths crucial for fitting tasks. In: International Conference on Machine Learning, pp. 36958\u201336977. PMLR (2023)"},{"key":"6_CR55","unstructured":"Wulfmeier, M., Ondruska, P., Posner, I.: Maximum entropy deep inverse reinforcement learning. arXiv preprint arXiv:1507.04888 (2015)"},{"issue":"2","key":"6_CR56","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1109\/LRA.2020.2969931","volume":"5","author":"M Yan","year":"2020","unstructured":"Yan, M., Zhu, Y., Jin, N., Bohg, J.: Self-supervised learning of state estimation for manipulating deformable linear objects. IEEE Robot. Autom. Lett. 5(2), 2372\u20132379 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"6_CR57","unstructured":"Yang, S., Nachum, O., Du, Y., Wei, J., Abbeel, P., Schuurmans, D.: Foundation models for decision making: problems, methods, and opportunities. arXiv preprint arXiv:2303.04129 (2023)"},{"key":"6_CR58","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR59","unstructured":"Yu, W., et\u00a0al.: Language to rewards for robotic skill synthesis. arXiv preprint arXiv:2306.08647 (2023)"},{"key":"6_CR60","unstructured":"Zakka, K., Zeng, A., Florence, P., Tompson, J., Bohg, J., Dwibedi, D.: Xirl: cross-embodiment inverse reinforcement learning. In: Conference on Robot Learning, pp. 537\u2013546. PMLR (2022)"},{"key":"6_CR61","unstructured":"Zeng, A., et\u00a0al.: Transporter networks: rearranging the visual world for robotic manipulation. In: Conference on Robot Learning, pp. 726\u2013747. PMLR (2021)"}],"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\/978-3-031-72897-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:17:24Z","timestamp":1733095044000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72897-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031728969","9783031728976"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72897-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 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"}}]}}