{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:58:18Z","timestamp":1761649098946,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031205026"},{"type":"electronic","value":"9783031205033"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20503-3_17","type":"book-chapter","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:09:06Z","timestamp":1671192546000},"page":"208-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Skill Chaining with Diversity for Multi-agent Systems*"],"prefix":"10.1007","author":[{"given":"Zaipeng","family":"Xie","sequence":"first","affiliation":[]},{"given":"Cheng","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Yufeng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,17]]},"reference":[{"issue":"2","key":"17_CR1","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer, S., Diepold, K.: Multi-agent deep reinforcement learning: a survey. Artif. Intell. Rev. 55(2), 895\u2013943 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Kang, Y., Wang, X., et al.: Q-adaptive: a multi-agent reinforcement learning based routing on dragonfly network. In: Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing, pp. 189\u2013200 (2021)","DOI":"10.1145\/3431379.3460650"},{"issue":"11","key":"17_CR3","doi-asserted-by":"publisher","first-page":"4948","DOI":"10.3390\/app11114948","volume":"11","author":"L Canese","year":"2021","unstructured":"Canese, L., Cardarilli, G.C., Di Nunzio, L., et al.: Multi-agent reinforcement learning: a review of challenges and applications. Appl. Sci. 11(11), 4948 (2021)","journal-title":"Appl. Sci."},{"key":"17_CR4","unstructured":"Ma, J., Wu, F.: Feudal multi-agent deep reinforcement learning for traffic signal control. In: Proceedings of International Conference on Autonomous Agents and MultiAgent Systems, pp. 816\u2013824. AAMAS (2020)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Su, J., Adams, S.C., et al.: Value-decomposition multi-agent actor-critics. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11352\u201311360 (2021)","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Sarafian, E., Tamar, A., Kraus, S.: Constrained policy improvement for efficient reinforcement learning. In: International Joint Conference on Artificial Intelligence, IJCAI, pp. 2863\u20132871 (2020)","DOI":"10.24963\/ijcai.2020\/396"},{"key":"17_CR7","unstructured":"Terry, J.K., Black, B., Grammel, N., et al.: Pettingzoo: gym for multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 15032\u201315043 (2021)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, Y., Gao, Y., et al.: Value function transfer for deep multi-agent reinforcement learning based on N-step returns. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI, pp. 457\u2013463 (2019)","DOI":"10.24963\/ijcai.2019\/65"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Phan, T., Belzner, L., et al.: Resilient multi-agent reinforcement learning with adversarial value decomposition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11308\u201311316 (2021)","DOI":"10.1609\/aaai.v35i13.17348"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Danassis, P., Wiedemair, F., et al.: Improving multi-agent coordination by learning to estimate contention. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI, pp. 125\u2013131 (2021)","DOI":"10.24963\/ijcai.2021\/18"},{"key":"17_CR11","unstructured":"Rashid, T., Samvelyan, M., et al.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the International Conference on Machine Learning, ICML, vol. 80, pp. 4292\u20134301 (2018)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Bacon, P., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1726\u20131734 (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"17_CR13","unstructured":"Tang, H., Hao, J., Lv, T., et al.: Hierarchical deep multiagent reinforcement learning. CoRR abs\/1809.09332 (2018)"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Tessler, C., Givony, S., Zahavy, T., et al.: A deep hierarchical approach to lifelong learning in MineCraft. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"17_CR15","unstructured":"Andrychowicz, M., Crow, D., Ray, A., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 5048\u20135058 (2017)"},{"key":"17_CR16","unstructured":"Bagaria, A., Konidaris, G.: Option discovery using deep skill chaining. In: International Conference on Learning Representations, ICLR (2020)"},{"key":"17_CR17","unstructured":"Sharma, A., Gu, S., Levine, S., et al.: Dynamics-aware unsupervised discovery of skills. In: International Conference on Learning Representations, ICLR (2019)"},{"key":"17_CR18","unstructured":"Sayin, M., Zhang, K., Leslie, D., et al.: Decentralized Q-learning in zero-sum markov games. In: Advances in Neural Information Processing Systems, NeurIPS, vol. 34, pp. 18320\u201318334 (2021)"},{"key":"17_CR19","unstructured":"Engstrom, L., Ilyas, A., Santurkar, S., et al.: Implementation matters in deep RL: a case study on PPO and TRPO. In: International Conference on Learning Representations, ICLR (2020)"},{"key":"17_CR20","unstructured":"Osband, I., Blundell, C., Pritzel, A., et al.: Deep exploration via bootstrapped DQN. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 4026\u20134034 (2016)"},{"key":"17_CR21","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the International Conference on Machine Learning, ICML, vol. 48, pp. 1928\u20131937 (2016)"},{"key":"17_CR22","unstructured":"Kulkarni, T.D., Narasimhan, K., et al.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 3675\u20133683 (2016)"},{"issue":"7540","key":"17_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"17_CR24","unstructured":"Kim, J., Park, S., Kim, G.: Unsupervised skill discovery with bottleneck option learning. In: Proceedings of the International Conference on Machine Learning, ICML, vol. 139, pp. 5572\u20135582 (2021)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Lin, Y., Gou, Y., Liu, Z., et al.: COMPLETER: incomplete multi-view clustering via contrastive prediction. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 11174\u201311183 (2021)","DOI":"10.1109\/CVPR46437.2021.01102"},{"key":"17_CR26","unstructured":"Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., et al.: Learning deep representations by mutual information estimation and maximization. In: International Conference on Learning Representations, ICLR (2019)"},{"key":"17_CR27","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: Advances in Neural Information Processing Systems, NeurIPS, pp. 15509\u201315519 (2019)"},{"key":"17_CR28","unstructured":"Samvelyan, M., Rashid, T., de Witt, C.S., et al.: The StarCraft Multi-Agent Challenge. CoRR abs\/1902.04043 (2019)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20503-3_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:32:58Z","timestamp":1671193978000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20503-3_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031205026","9783031205033"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20503-3_17","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":"17 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","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":"472","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":"164","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":"35% - 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":"3.1","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":"3.7","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)"}}]}}