{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T14:26:51Z","timestamp":1783348011378,"version":"3.54.6"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032306920","type":"print"},{"value":"9783032306937","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"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\/978-3-032-30693-7_27","type":"book-chapter","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T14:06:14Z","timestamp":1783346774000},"page":"420-438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incremental Reinforcement Learning with\u00a0Temporally Dependent Goals"],"prefix":"10.1007","author":[{"given":"Yi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shufang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"De Giacomo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinchao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongdong","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"27_CR1","unstructured":"Connell, J.H., Mahadevan, S. (eds.): Robot learning. Kluwer, Boston (1993\/1997). Robotica 17(2), 229\u2013235 (1999)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Camacho, A., Icarte, R.T., Klassen, T.Q., Valenzano, R.A., McIlraith, S.A.: LTL and beyond: formal languages for reward function specification in reinforcement learning. In: IJCAI, pp. 6065\u20136073 (2019)","DOI":"10.24963\/ijcai.2019\/840"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"De Giacomo, G., Di Stasio, A., Tabajara, L.M., Vardi, M.Y., Zhu, S.: Finite-trace and generalized-reactivity specifications in temporal synthesis. In: IJCAI, pp. 1852\u20131858 (2021)","DOI":"10.24963\/ijcai.2021\/255"},{"issue":"2","key":"27_CR5","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s10703-023-00413-2","volume":"61","author":"G De Giacomo","year":"2022","unstructured":"De Giacomo, G., Di Stasio, A., Tabajara, L.M., Vardi, M.Y., Zhu, S.: Finite-trace and generalized-reactivity specifications in temporal synthesis. Formal Methods Syst. Des. 61(2), 139\u2013163 (2022)","journal-title":"Formal Methods Syst. Des."},{"key":"27_CR6","unstructured":"De Giacomo, G., Vardi, M.Y.: Linear temporal logic and linear dynamic logic on finite traces. In: IJCAI, pp. 854\u2013860 (2013)"},{"key":"27_CR7","unstructured":"Fakoor, R., Chaudhari, P., Soatto, S., Smola, A.J.: Meta-q-learning. CoRR abs\/1910.00125 (2019)"},{"key":"27_CR8","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: ICML, pp. 1587\u20131596 (2018)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Grigsby, J., Sasek, J., Parajuli, S., Adebi, D., Zhang, A., Zhu, Y.: AMAGO-2: breaking the multi-task barrier in meta-reinforcement learning with transformers. In: NeurIPS, pp. 87473\u201387508 (2024)","DOI":"10.52202\/079017-2776"},{"key":"27_CR10","doi-asserted-by":"publisher","first-page":"103949","DOI":"10.1016\/j.artint.2023.103949","volume":"322","author":"H Hasanbeig","year":"2023","unstructured":"Hasanbeig, H., Kroening, D., Abate, A.: Certified reinforcement learning with logic guidance. Artif. Intell. 322, 103949 (2023)","journal-title":"Artif. Intell."},{"key":"27_CR11","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Logically-constrained reinforcement learning (2019)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Icarte, R.T., Klassen, T.Q., Valenzano, R.A., McIlraith, S.A.: Teaching multiple tasks to an RL agent using LTL. In: AAMAS, pp. 452\u2013461 (2018)","DOI":"10.65109\/FKNQ6967"},{"key":"27_CR13","unstructured":"Jackermeier, M., Abate, A.: DeepLTL: learning to efficiently satisfy complex LTL specifications for multi-task RL. In: ICLR (2025)"},{"key":"27_CR14","unstructured":"Jothimurugan, K., Bansal, S., Bastani, O., Alur, R.: Specification-guided reinforcement learning. In: Neural and Symbolic Learning and Reasoning (NeuS), pp. 316\u2013330 (2025)"},{"issue":"6","key":"27_CR15","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2022","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"11","key":"27_CR16","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Lichtenstein, O., Pnueli, A., Zuck, L.D.: The glory of the past. In: Logic of Programs, pp. 196\u2013218 (1985)","DOI":"10.1007\/3-540-15648-8_16"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Liu, M., Zhu, M., Zhang, W.: Goal-conditioned reinforcement learning: problems and solutions. In: IJCAI-22, pp. 5502\u20135511 (2022). survey Track","DOI":"10.24963\/ijcai.2022\/770"},{"key":"27_CR19","unstructured":"Pan, C., et al.: A survey of continual reinforcement learning. CoRR abs\/2506.21872 (2025)"},{"key":"27_CR20","unstructured":"Plappert, M., et\u00a0al.: Multi-goal reinforcement learning: challenging robotics environments and request for research. arXiv preprint: arXiv:1802.09464 (2018)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Pnueli, A.: The temporal logic of programs. In: FOCS, pp. 46\u201357 (1977)","DOI":"10.1109\/SFCS.1977.32"},{"key":"27_CR22","first-page":"39147","volume":"36","author":"W Qiu","year":"2023","unstructured":"Qiu, W., Mao, W., Zhu, H.: Instructing goal-conditioned reinforcement learning agents with temporal logic objectives. NeurIPS 36, 39147\u201339175 (2023)","journal-title":"NeurIPS"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Sadigh, D., Kim, E.S., Coogan, S., Sastry, S.S., Seshia, S.A.: A learning based approach to control synthesis of Markov decision processes for linear temporal logic specifications. In: CDC, pp. 1091\u20131096 (2014)","DOI":"10.1109\/CDC.2014.7039527"},{"key":"27_CR24","unstructured":"Shala, G., Biedenkapp, A., Grabocka, J.: Hierarchical transformers are efficient meta-reinforcement learners (2024)"},{"key":"27_CR25","unstructured":"Shao, K., Tang, Z., Zhu, Y., Li, N., Zhao, D.: A survey of deep reinforcement learning in video games (2019)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Shukla, Y., Burman, T., Kulkarni, A., Wright, R., Velasquez, A., Sinapov, J.: Logical specifications-guided dynamic task sampling for reinforcement learning agents. In: ICAPS, pp. 532\u2013540 (2024)","DOI":"10.1609\/icaps.v34i1.31514"},{"key":"27_CR27","unstructured":"Sodhani, S., Zhang, A., Pineau, J.: Multi-task reinforcement learning with context-based representations (2021)"},{"key":"27_CR28","unstructured":"Svoboda, J., Bansal, S., Chatterjee, K.: Reinforcement learning from reachability specifications: PAC guarantees with expected conditional distance. In: ICML (2024)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Szita, I.: Reinforcement Learning in Games, pp. 539\u2013577. Springer Berlin Heidelberg, Berlin, Heidelberg (2012)","DOI":"10.1007\/978-3-642-27645-3_17"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Toro\u00a0Icarte, R., Klassen, T.Q., Valenzano, R., McIlraith, S.A.: Teaching multiple tasks to an RL agent using LTL. In: AAMAS, pp. 452\u2013461 (2018)","DOI":"10.65109\/FKNQ6967"},{"key":"27_CR31","unstructured":"Vaezipoor, P., Li, A.C., Icarte, R.A.T., Mcilraith, S.A.: LTL2Action: generalizing LTL instructions for multi-task RL. In: International Conference on Machine Learning, pp. 10497\u201310508. PMLR (2021)"},{"issue":"2","key":"27_CR32","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1109\/TMECH.2019.2899365","volume":"24","author":"Z Wang","year":"2019","unstructured":"Wang, Z., Chen, C., Li, H.X., Dong, D., Tarn, T.J.: Incremental reinforcement learning with prioritized sweeping for dynamic environments. IEEE\/ASME Trans. Mechatron. 24(2), 621\u2013632 (2019)","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Yalcinkaya, B., Lauffer, N., Vazquez-Chanlatte, M., Seshia, S.A.: Compositional automata embeddings for goal-conditioned reinforcement learning. In: NeurIPS (2024)","DOI":"10.52202\/079017-2322"}],"container-title":["Lecture Notes in Computer Science","Theoretical Aspects of Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-30693-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T14:07:09Z","timestamp":1783346829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-30693-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"ISBN":["9783032306920","9783032306937"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-30693-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TASE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Theoretical Aspects of Software Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tase2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tase2026.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}