{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:55:39Z","timestamp":1743090939486,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031208676"},{"type":"electronic","value":"9783031208683"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20868-3_7","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:29:12Z","timestamp":1667518152000},"page":"91-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DDMA: Discrepancy-Driven Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Chao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinzhuo","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaokang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"issue":"1","key":"7_CR1","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2012","unstructured":"Cao, Y., Yu, W., Ren, W., Chen, G.: An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans. Industr. Inf. 9(1), 427\u2013438 (2012)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"7_CR2","unstructured":"Christianos, F., Sch\u00e4fer, L., Albrecht, S.: Shared experience actor-critic for multi-agent reinforcement learning, vol. 33, pp. 10707\u201310717 (2020)"},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1613\/jair.1.11396","volume":"64","author":"FL Da Silva","year":"2019","unstructured":"Da Silva, F.L., Costa, A.H.R.: A survey on transfer learning for multiagent reinforcement learning systems. J. Artif. Intell. Res. 64, 645\u2013703 (2019)","journal-title":"J. Artif. Intell. Res."},{"key":"7_CR4","unstructured":"De Hauwere, Y.M., Vrancx, P., Now\u00e9, A.: Learning multi-agent state space representations. In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, vol. 1, pp. 715\u2013722 (2010)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Diuk, C., Cohen, A., Littman, M.L.: An object-oriented representation for efficient reinforcement learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 240\u2013247 (2008)","DOI":"10.1145\/1390156.1390187"},{"key":"7_CR6","unstructured":"Farquhar, G., Gustafson, L., Lin, Z., Whiteson, S., Usunier, N., Synnaeve, G.: Growing action spaces. In: International Conference on Machine Learning. PMLR, pp. 3040\u20133051 (2020)"},{"key":"7_CR7","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. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"7_CR8","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"key":"7_CR9","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol. 2, pp. 2672\u20132680 (2014)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, S., Mu, Z., Long, X., Chu, S., Zhao, G.: A multi-agent reinforcement learning method for swarm robots in space collaborative exploration. In: 2020 6th International Conference on Control, Automation and Robotics (ICCAR), pp. 139\u2013144. IEEE (2020)","DOI":"10.1109\/ICCAR49639.2020.9107997"},{"key":"7_CR11","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning. PMLR, pp. 2961\u20132970 (2019)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, Y., Gao, Y., Chen, Y., Fan, C.: Value function transfer for deep multi-agent reinforcement learning based on n-step returns. In: IJCAI, pp. 457\u2013463 (2019)","DOI":"10.24963\/ijcai.2019\/65"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7211\u20137218 (2020)","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"7_CR14","unstructured":"Long, Q., Zhou, Z., Gupta, A., Fang, F., Wu, Y., Wang, X.: Evolutionary population curriculum for scaling multi-agent reinforcement learning. arXiv preprint arXiv:2003.10423 (2020)"},{"key":"7_CR15","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv preprint arXiv:1706.02275 (2017)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"7_CR17","first-page":"1","volume":"21","author":"S Narvekar","year":"2020","unstructured":"Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M.E., Stone, P.: Curriculum learning for reinforcement learning domains: a framework and survey. J. Mach. Learn. Res. 21, 1\u201350 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Omidshafiei, S., et al.: Learning to teach in cooperative multiagent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6128\u20136136 (2019)","DOI":"10.1609\/aaai.v33i01.33016128"},{"key":"7_CR19","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning. PMLR, pp. 4295\u20134304 (2018)"},{"key":"7_CR20","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 2186\u20132188 (2019)"},{"key":"7_CR21","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning. PMLR, pp. 5887\u20135896 (2019)"},{"key":"7_CR22","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"7_CR23","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"key":"7_CR24","unstructured":"Vezhnevets, A., Wu, Y., Eckstein, M., Leblond, R., Leibo, J.Z.: Options as responses: grounding behavioural hierarchies in multi-agent reinforcement learning. In: International Conference on Machine Learning. PMLR, pp. 9733\u20139742 (2020)"},{"key":"7_CR25","unstructured":"Wang, J., Ren, Z., Liu, T., Yu, Y., Zhang, C.: QPLEX: duplex dueling multi-agent Q-learning. arXiv preprint arXiv:2008.01062 (2020)"},{"key":"7_CR26","unstructured":"Wang, T., Gupta, T., Mahajan, A., Peng, B., Whiteson, S., Zhang, C.: RODE: learning roles to decompose multi-agent tasks. arXiv preprint arXiv:2010.01523 (2020)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: From few to more: large-scale dynamic multiagent curriculum learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7293\u20137300 (2020)","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"7_CR28","unstructured":"Yang, T., et al.: An efficient transfer learning framework for multiagent reinforcement learning, vol. 34 (2021)"},{"key":"7_CR29","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning. PMLR, pp. 5571\u20135580 (2018)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2022: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20868-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:39:01Z","timestamp":1667518741000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20868-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208676","9783031208683"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20868-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shangai","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pricai.org\/2022\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"432","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":"91","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":"39","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":"21% - 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":"7-8","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":"n\/a","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}