{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:44:50Z","timestamp":1743021890885,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031264115"},{"type":"electronic","value":"9783031264122"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26412-2_15","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T10:03:54Z","timestamp":1678961034000},"page":"233-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DistSPECTRL: Distributing Specifications in\u00a0Multi-Agent Reinforcement Learning Systems"],"prefix":"10.1007","author":[{"given":"Joe","family":"Eappen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suresh","family":"Jagannathan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"15_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: NIPS (2017)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Camacho, A., Toro Icarte, R., Klassen, T.Q., Valenzano, R., McIlraith, S.A.: LTL and beyond: formal languages for reward function specification in RL. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/840"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"15_CR4","unstructured":"Hammond, L., Abate, A., Gutierrez, J., Wooldridge, M.: Multi-agent reinforcement learning with temporal logic specifications. In: AAMAS (2021)"},{"key":"15_CR5","unstructured":"Jothimurugan, K., Alur, R., Bastani, O.: A composable specification language for reinforcement learning tasks. In: NeurIPS (2019)"},{"key":"15_CR6","unstructured":"Jothimurugan, K., Bansal, S., Bastani, O., Alur, R.: Compositional reinforcement learning from logical specifications. In: NeurIPS (2021)"},{"key":"15_CR7","unstructured":"Le, H.M., Yue, Y., Carr, P., Lucey, P.: Coordinated MA imitation learning. In: ICML (2017)"},{"key":"15_CR8","unstructured":"Li, X., Vasile, C., Belta, C.: RL with temporal logic rewards. In: IROS (2017)"},{"key":"15_CR9","unstructured":"Liang, E., et al.: RLlib: abstractions for distributed reinforcement learning. In: ICML (2018)"},{"key":"15_CR10","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"key":"15_CR11","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NIPS (2017)"},{"key":"15_CR12","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search of static linear policies is competitive for reinforcement learning. In: NeurIPS (2018)"},{"key":"15_CR13","unstructured":"Neary, C., Xu, Z., Wu, B., Topcu, U.: Reward machines for cooperative multi-agent reinforcement learning. In: AAMAS (2021)"},{"key":"15_CR14","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML (1999)"},{"key":"15_CR15","unstructured":"Samvelyan, M., et al.: Starcraft challenge. In: AAMAS (2019)"},{"key":"15_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR (2017)"},{"key":"15_CR17","unstructured":"Song, J., Ren, H., Sadigh, D., Ermon, S.: Multi-agent generative adversarial imitation learning. In: NeurIPS (2018)"},{"key":"15_CR18","unstructured":"Toro Icarte, R., Klassen, T.Q., Valenzano, R., McIlraith, S.A.: Using reward machines for high-level task specification and decomposition in reinforcement learning. In: ICML (2018)"},{"key":"15_CR19","unstructured":"Toro Icarte, R., Klassen, T.Q., Valenzano, R., McIlraith, S.A.: Reward machines: exploiting reward function structure in reinforcement learning. arXiv preprint arXiv:2010.03950 (2020)"},{"key":"15_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/inco.1994.1092","volume":"115","author":"M Vardi","year":"1994","unstructured":"Vardi, M., Wolper, P.: Reasoning about infinite computations. Inf. Comp. 115, 1\u201337 (1994)","journal-title":"Inf. Comp."},{"key":"15_CR21","unstructured":"Vazquez-Chanlatte, M., Jha, S., Tiwari, A., Ho, M.K., Seshia, S.: Learning task specifications from demonstrations. In: NeurIPS (2018)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: From few to more: large-scale dynamic multiagent curriculum learning. In: AAAI, no. 05 (2020)","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"15_CR23","unstructured":"Yu, L., Song, J., Ermon, S.: Multi-agent adversarial inverse RL. In: ICML (2019)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26412-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T10:07:29Z","timestamp":1678961249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26412-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264115","9783031264122"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26412-2_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 March 2023","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":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"236","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17 demo track papers have been accepted from 28 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}