{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:13:45Z","timestamp":1743045225736,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031746499"},{"type":"electronic","value":"9783031746505"}],"license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"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\/978-3-031-74650-5_5","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T15:51:19Z","timestamp":1732809079000},"page":"82-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Counterfactual Communication Using Difference Rewards Policy Gradients"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9664-9925","authenticated-orcid":false,"given":"Simon","family":"Vanneste","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6742-6722","authenticated-orcid":false,"given":"Astrid","family":"Vanneste","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2969-3133","authenticated-orcid":false,"given":"Tom","family":"De Schepper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9355-6566","authenticated-orcid":false,"given":"Siegfried","family":"Mercelis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8029-4720","authenticated-orcid":false,"given":"Peter","family":"Hellinckx","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4812-4841","authenticated-orcid":false,"given":"Kevin","family":"Mets","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,2]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Castellini, J., Devlin, S., Oliehoek, F.A., Savani, R.: Difference rewards policy gradients (2021)","key":"5_CR1","DOI":"10.1007\/s00521-022-07960-5"},{"unstructured":"Chang, Y.H., Ho, T., Kaelbling, L.: All learning is local: multi-agent learning in global reward games. In: Advances in Neural Information Processing Systems, vol. 16 (2003)","key":"5_CR2"},{"unstructured":"Das, A., et al.: Tarmac: targeted multi-agent communication. In: International Conference on Machine Learning, pp. 1538\u20131546. PMLR (2019)","key":"5_CR3"},{"unstructured":"Foerster, J., Assael, I.A., De\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)","key":"5_CR4"},{"doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","key":"5_CR5","DOI":"10.1609\/aaai.v32i1.11794"},{"unstructured":"Jaques, N., et al.: Social influence as intrinsic motivation for multi-agent deep reinforcement learning. In: International Conference on Machine Learning, pp. 3040\u20133049. PMLR (2019)","key":"5_CR6"},{"unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"5_CR7"},{"unstructured":"Lyu, X., Xiao, Y., Daley, B., Amato, C.: Contrasting centralized and decentralized critics in multi-agent reinforcement learning (2021)","key":"5_CR8"},{"unstructured":"Mandhane, A., et\u00a0al.: Muzero with self-competition for rate control in vp9 video compression. arXiv preprint arXiv:2202.06626 (2022)","key":"5_CR9"},{"unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)","key":"5_CR10"},{"issue":"7540","key":"5_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"5_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A Concise Introduction to Decentralized POMDPs. Springer, Cham (2016)"},{"doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Vlassis, N.: Q-value functions for decentralized POMDPs. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, pp.\u00a01\u20138 (2007)","key":"5_CR13","DOI":"10.1145\/1329125.1329390"},{"unstructured":"Van\u00a0der Pol, E., Oliehoek, F.A.: Coordinated deep reinforcement learners for traffic light control. In: Proceedings of Learning, Inference and Control of Multi-Agent Systems (at NIPS 2016) (2016)","key":"5_CR14"},{"unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. PMLR (2014)","key":"5_CR15"},{"unstructured":"Sukhbaatar, S., Fergus, R., et\u00a0al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)","key":"5_CR16"},{"key":"5_CR17","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)","edition":"1"},{"doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a030 (2016)","key":"5_CR18","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"5_CR19","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-030-89899-1_21","volume-title":"Advances on P2P, Parallel, Grid, Cloud and Internet Computing","author":"S Vanneste","year":"2022","unstructured":"Vanneste, S., et al.: Learning to communicate with reinforcement learning for an adaptive traffic control system. In: Barolli, L. (ed.) 3PGCIC 2021. LNNS, vol. 343, pp. 207\u2013216. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-89899-1_21"},{"unstructured":"Vanneste, S., et al.: Learning to communicate using counterfactual reasoning. In: Proceedings of the Adaptive and Learning Agents Workshop (ALA 2022). Adaptive and Learning Agents Workshop (ALA 2022) (2022)","key":"5_CR20"},{"doi-asserted-by":"crossref","unstructured":"Wolpert, D.H., Tumer, K.: Optimal payoff functions for members of collectives. Adv. Complex Syst. 4(02n03), 265\u2013279 (2001)","key":"5_CR21","DOI":"10.1142\/S0219525901000188"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence and Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-74650-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T16:03:36Z","timestamp":1732809816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-74650-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,2]]},"ISBN":["9783031746499","9783031746505"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-74650-5_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024,11,2]]},"assertion":[{"value":"2 November 2024","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":"BNAIC\/Benelearn","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benelux Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bnaic2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bnaic2023.tudelft.nl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}