{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:47:28Z","timestamp":1782312448345,"version":"3.54.5"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061058","type":"print"},{"value":"9783032061065","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"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\/978-3-032-06106-5_12","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:08:52Z","timestamp":1759399732000},"page":"198-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalization of\u00a0Compositional Tasks with\u00a0Logical Specification via\u00a0Implicit Planning"],"prefix":"10.1007","author":[{"given":"Duo","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faramarz","family":"Fekri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"12_CR1","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":"12_CR2","unstructured":"Araki, B., Li, X., Vodrahalli, K., DeCastro, J., Fry, M., Rus, D.: The logical options framework. In: International Conference on Machine Learning, pp. 307\u2013317. PMLR (2021)"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Araki, B., Vodrahalli, K., Leech, T., Vasile, C.I., Donahue, M.D., Rus, D.L.: Learning to plan with logical automata (2019)","DOI":"10.15607\/RSS.2019.XV.064"},{"key":"12_CR4","unstructured":"Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. Adv. Neural Info. Process. Syst.26 (2013)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Camacho, A., Icarte, R.T., Klassen, T.Q., Valenzano, R.A., McIlraith, S.A.: Formal languages for reward function specification in reinforcement learning. In: IJCAI, Ltl and beyond (2019)","DOI":"10.24963\/ijcai.2019\/840"},{"key":"12_CR6","unstructured":"Chane-Sane, E., Schmid, C., Laptev, I.: Goal-conditioned reinforcement learning with imagined subgoals. In: International Conference on Machine Learning, pp. 1430\u20131440. PMLR (2021)"},{"key":"12_CR7","unstructured":"De\u00a0Giacomo, G., Vardi, M.Y.: Linear temporal logic and linear dynamic logic on finite traces. In: IJCAI\u201913 Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, pp. 854\u2013860. Association for Computing Machinery (2013)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Hengst, F.D., Fran\u00e7ois-Lavet, V., Hoogendoorn, M., van Harmelen, F.: Reinforcement learning with option machines. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 2909\u20132915. International Joint Conferences on Artificial Intelligence Organization (2022)","DOI":"10.24963\/ijcai.2022\/403"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Gujarathi, D., Saha, I.: Mt*: multi-robot path planning for temporal logic specifications. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.13692\u201313699. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981504"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Lahijanian, M., Kavraki, L.E., Vardi, M.Y.: Towards manipulation planning with temporal logic specifications. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 346\u2013352. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139022"},{"key":"12_CR11","unstructured":"Icarte, R.T., Klassen, T., Valenzano, R., McIlraith, S.: Using reward machines for high-level task specification and decomposition in reinforcement learning. In: International Conference on Machine Learning, pp. 2107\u20132116. PMLR (2018)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Icarte, R.T., Klassen, T.Q., Valenzano, R., McIlraith, R.S.: Exploiting reward function structure in reinforcement learning: reward machines. J. Artif. Intell. Res. 73, 173\u2013208 (2022)","DOI":"10.1613\/jair.1.12440"},{"key":"12_CR13","unstructured":"Jothimurugan, K., Alur, R., Bastani, O.: A composable specification language for reinforcement learning tasks. Adv. Neural Info. Process. Syst.32 (2019)"},{"key":"12_CR14","first-page":"10026","volume":"34","author":"K Jothimurugan","year":"2021","unstructured":"Jothimurugan, K., Bansal, S., Bastani, O., Alur, R.: Compositional reinforcement learning from logical specifications. Adv. Neural. Inf. Process. Syst. 34, 10026\u201310039 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Khalidi, D., Gujarathi, D., Indranil Saha, T: A heuristic search based path planning algorithm for temporal logic specifications. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 8476\u20138482. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196928"},{"key":"12_CR16","unstructured":"Kipf, T., van\u00a0der Pol, E., Welling, M.: Contrastive learning of structured world models. In: International Conference on Learning Representations (2020)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Kuo, Y., Katz, B., Barbu, A.: Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5604\u20135610. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341325"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Kuric, D., Infante, G., G\u00f3mez, V., Jonsson, A., van Hoof, H.: Planning with a learned policy basis to optimally solve complex tasks. In: Proceedings of the International Conference on Automated Planning and Scheduling vol. 34, pp. 333\u2013341 (2024)","DOI":"10.1609\/icaps.v34i1.31492"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1023\/A:1016619613658","volume":"30","author":"J Kvarnstr\u00f6m","year":"2000","unstructured":"Kvarnstr\u00f6m, J., Doherty, P.: Talplanner: a temporal logic based forward chaining planner. Ann. Math. Artif. Intell. 30, 119\u2013169 (2000)","journal-title":"Ann. Math. Artif. Intell."},{"key":"12_CR20","unstructured":"G Le\u00f3n, B., Shanahan, M., Belardinelli, F.: Systematic generalisation through task temporal logic and deep reinforcement learning. arXiv preprint arXiv:2006.08767 (2020)"},{"key":"12_CR21","unstructured":"G Le\u00f3n, B., Shanahan, M., Belardinelli, F.: In a nutshell, the human asked for this: latent goals for following temporal specifications. In: International Conference on Learning Representations (2021)"},{"key":"12_CR22","unstructured":"Li, S., Zhang, J., Wang, J., Yu, Y., Zhang, C.: Active hierarchical exploration with stable subgoal representation learning. arXiv preprint arXiv:2105.14750, 2021"},{"key":"12_CR23","unstructured":"Littman, M.L., Topcu, U., Fu, J., Isbell, C., Wen, M., MacGlashan, J.: Environment-independent task specifications via GLTL. arXiv preprint arXiv:1704.04341, 2017"},{"key":"12_CR24","unstructured":"Xinyu Liu, J., Shah, A., Rosen, E., Konidaris, G., Tellex, S.: Skill transfer for temporally-extended task specifications. arXiv preprint arXiv:2206.05096, 2022"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Liu, M., Zhu, M., Zhang, W.: Goal-conditioned reinforcement learning: Problems and solutions. arXiv preprint arXiv:2201.08299, 2022","DOI":"10.24963\/ijcai.2022\/770"},{"key":"12_CR26","unstructured":"Mnih, V.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning. Nature518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Pnueli, A.: The temporal logic of programs. In: 18th Annual Symposium on Foundations of Computer Science (SFCS 1977), pp. 46\u201357. IEEE (1977)","DOI":"10.1109\/SFCS.1977.32"},{"key":"12_CR29","unstructured":"Ray, A., Achiam, J., Amodei, D.: Benchmarking safe exploration in deep reinforcement learning. arXiv preprint arXiv:1910.01708, 7:1 (2019)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw.20(1), 61\u201380 (2008)","DOI":"10.1109\/TNN.2008.2005605"},{"key":"12_CR31","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"12_CR32","unstructured":"Sutton, R.S., Barto, R.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res.10(7) (2009)","DOI":"10.1007\/978-3-642-01882-4_2"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Icarte, R.T., Klassen, T.Q., Valenzano, R., McIlraith, S.A.: Teaching multiple tasks to an RL agent using LTL. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, pp. 452\u2013461 (2018)","DOI":"10.65109\/FKNQ6967"},{"key":"12_CR35","unstructured":"Vaezipoor, P., Li, A.C., Icarte, R.A.C., Mcilraith, S.A.: Ltl2action: generalizing LTL instructions for multi-task RL. In: International Conference on Machine Learning, pp. 10497\u201310508. PMLR (2021)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"van\u00a0der Pol, E., Kipf, T., Oliehoek, F.A., Welling, M.: Plannable approximations to MDP homomorphisms: equivariance under actions. In: Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020, vol. 2020. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) (2020)","DOI":"10.65109\/DAIE3353"},{"key":"12_CR37","unstructured":"Voloshin, C., Verma, A., Yue, Y.: Eventual discounting temporal logic counterfactual experience replay. In: International Conference on Machine Learning, pp. 35137\u201335150. PMLR (2023)"},{"issue":"4","key":"12_CR38","doi-asserted-by":"publisher","first-page":"5064","DOI":"10.1109\/TNNLS.2022.3207346","volume":"35","author":"X Wang","year":"2022","unstructured":"Wang, X., et al.: Deep reinforcement learning: a survey. IEEE Trans. Neural Netw. Learn. Syst. 35(4), 5064\u20135078 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Xu, D., Fekri, F.: Generalization of temporal logic tasks via future dependent options. Mach. Learn., pp. 1\u201332 (2024)","DOI":"10.1007\/s10994-024-06614-y"},{"key":"12_CR40","doi-asserted-by":"publisher","first-page":"72933","DOI":"10.52202\/079017-2322","volume":"37","author":"B Yalcinkaya","year":"2024","unstructured":"Yalcinkaya, B., Lauffer, N., Vazquez-Chanlatte, M., Seshia, S.: Compositional automata embeddings for goal-conditioned reinforcement learning. Adv. Neural. Inf. Process. Syst. 37, 72933\u201372963 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR41","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","volume":"1","author":"J Zhou","year":"2020","unstructured":"Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI open 1, 57\u201381 (2020)","journal-title":"AI open"}],"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\/978-3-032-06106-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:03:24Z","timestamp":1782309804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"3 October 2025","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"}}]}}