{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:47:36Z","timestamp":1759402056406,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":12,"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_5","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:08:33Z","timestamp":1759399713000},"page":"77-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decentralizing Multi-agent Reinforcement Learning with\u00a0Temporal Causal Information"],"prefix":"10.1007","author":[{"given":"Jan","family":"Corazza","sequence":"first","affiliation":[]},{"given":"Hadi Partovi","family":"Aria","sequence":"additional","affiliation":[]},{"given":"Hyohun","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Neider","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Almeida, M., Moreira, N., Reis, R.: Testing the equivalence of regular languages. Electron. Proc. Theoretical Comput. Sci. 3, 47\u201357 (2009). https:\/\/doi.org\/10.4204\/EPTCS.3.4, http:\/\/arxiv.org\/abs\/0907.5058v1","DOI":"10.4204\/EPTCS.3.4"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"Azran, G., Danesh, M.H., Albrecht, S.V., Keren, S.: Contextual pre-planning on reward machine abstractions for enhanced transfer in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 10, pp. 10953\u201310961 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i10.28970, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/28970","DOI":"10.1609\/aaai.v38i10.28970"},{"key":"5_CR3","unstructured":"Corazza, J., Aria, H.P., Kim, H., Neider, D., Xu, Z.: Decentralizing multi-agent reinforcement learning with temporal causal information (2025). https:\/\/arxiv.org\/abs\/2506.07829"},{"key":"5_CR4","unstructured":"Corazza, J., Aria, H.P., Neider, D., Xu, Z.: Expediting reinforcement learning by incorporating knowledge about temporal causality in the environment. In: Locatello, F., Didelez, V. (eds.) Proceedings of the Third Conference on Causal Learning and Reasoning. In: Proceedings of Machine Learning Research, vol.\u00a0236, pp. 643\u2013664. PMLR (2024). https:\/\/proceedings.mlr.press\/v236\/corazza24a.html"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Dohmen, T., Topper, N., Atia, G., Beckus, A., Trivedi, A., Velasquez, A.: Inferring probabilistic reward machines from non-markovian reward processes for reinforcement learning (2022)","DOI":"10.1609\/icaps.v32i1.19844"},{"key":"5_CR6","unstructured":"Icarte, R.T., Klassen, T.Q., Valenzano, R.A., McIlraith, S.A.: Reward machines: exploiting reward function structure in reinforcement learning. CoRR abs\/2010.03950 (2020), https:\/\/arxiv.org\/abs\/2010.03950"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Kazemi, M., Perez, M., Somenzi, F., Soudjani, S., Trivedi, A., Velasquez, A.: Assume-guarantee reinforcement learning (2023)","DOI":"10.1609\/aaai.v38i19.30116"},{"key":"5_CR8","doi-asserted-by":"publisher","unstructured":"Neary, C., Xu, Z., Wu, B., Topcu, U.: Reward Machines for Cooperative Multi-Agent Reinforcement Learning (2021). https:\/\/doi.org\/10.5555\/3463952.3464063, http:\/\/arxiv.org\/abs\/2007.01962, arXiv:2007.01962 [cs]","DOI":"10.5555\/3463952.3464063"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Paliwal, Y., et al.: Reinforcement learning with temporal-logic-based causal diagrams (2023)","DOI":"10.1007\/978-3-031-40837-3_8"},{"key":"5_CR10","volume-title":"Introduction to the Theory of Computation","author":"M Sipser","year":"2013","unstructured":"Sipser, M.: Introduction to the Theory of Computation. MA, third edn, Course Technology, Boston (2013)"},{"key":"5_CR11","unstructured":"Wong, K.C.: On the complexity of projections of discrete-event systems. Discrete Event Dynamic Syst. (1998). https:\/\/api.semanticscholar.org\/CorpusID:17637223"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Xu, Z., et al.: Joint inference of reward machines and policies for reinforcement learning. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 30, pp. 590\u2013598 (2020). https:\/\/doi.org\/10.1609\/icaps.v30i1.6756, http:\/\/dx.doi.org\/10.1609\/icaps.v30i1.6756","DOI":"10.1609\/icaps.v30i1.6756"}],"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_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:08:37Z","timestamp":1759399717000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_5","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":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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"}}]}}