{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:13:51Z","timestamp":1743146031281,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030967710"},{"type":"electronic","value":"9783030967727"}],"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\/978-3-030-96772-7_36","type":"book-chapter","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T21:13:08Z","timestamp":1647378788000},"page":"396-411","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Model-Based Multi-agent Policy Optimization with Dynamic Dependence Modeling"],"prefix":"10.1007","author":[{"given":"Biyang","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zifan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,16]]},"reference":[{"issue":"7540","key":"36_CR1","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"},{"issue":"7587","key":"36_CR2","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"36_CR3","unstructured":"Toyama, D., et al.: Androidenv: a reinforcement learning platform for android. arXiv preprint arXiv:2105.13231 (2021)"},{"key":"36_CR4","unstructured":"Luo, Y., Xu, H., Li, Y., Tian, Y., Darrell, T., Ma, T.: Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees. arXiv preprint arXiv:1807.03858 (2018)"},{"key":"36_CR5","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":"36_CR6","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"36_CR7","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"36_CR8","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"36_CR9","unstructured":"Moerland, T.M., Broekens, J., Jonker, C.M.: Model-based reinforcement learning: a survey. arXiv preprint arXiv:2006.16712 (2020)"},{"key":"36_CR10","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"issue":"7839","key":"36_CR11","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"13","key":"36_CR13","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1049\/joe.2019.1200","volume":"2020","author":"Yu Chao","year":"2020","unstructured":"Chao, Yu., Dong, Y., Li, Y., Chen, Y.: Distributed multi-agent deep reinforcement learning for cooperative multi-robot pursuit. J. Eng. 2020(13), 499\u2013504 (2020)","journal-title":"J. Eng."},{"key":"36_CR14","unstructured":"Vinyals, O., et al.: Starcraft II: a new challenge for reinforcement learning. arXiv preprint arXiv:1708.04782 (2017)"},{"key":"36_CR15","unstructured":"Wu, Z., Yu, C., Ye, D., Zhang, J., Piao, H., Zhuo, H.H.: Coordinated proximal policy optimization. arXiv preprint arXiv:2111.04051 (2021)"},{"key":"36_CR16","unstructured":"Wang, R.E., et al.: Model-based reinforcement learning for decentralized multiagent rendezvous. In Conference on Robot Learning (CoRL), pp. 711\u2013725 (2020)"},{"issue":"2","key":"36_CR17","first-page":"735","volume":"21","author":"Yu Chao","year":"2019","unstructured":"Chao, Yu., et al.: Distributed multiagent coordinated learning for autonomous driving in highways based on dynamic coordination graphs. IEEE Trans. Intell. Transp. Syst. 21(2), 735\u2013748 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Willemsen, D., Coppola, M., Che de Croon, G.: Mambpo: sample-efficient multi-robot reinforcement learning using learned world models. arXiv preprint arXiv:2103.03662 (2021)","DOI":"10.1109\/IROS51168.2021.9635836"},{"issue":"12","key":"36_CR19","doi-asserted-by":"publisher","first-page":"2853","DOI":"10.1109\/TCYB.2014.2387277","volume":"45","author":"Yu Chao","year":"2015","unstructured":"Chao, Yu., Zhang, M., Ren, F., Tan, G.: Multiagent learning of coordination in loosely coupled multiagent systems. IEEE Trans. Cybernet. 45(12), 2853\u20132867 (2015)","journal-title":"IEEE Trans. Cybernet."},{"key":"36_CR20","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6382\u20136393 (2017)"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7559\u20137566. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"36_CR22","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems, pp. 4759\u20134770 (2018)"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Machine Learning Proceedings 1990, pp. 216\u2013224. Elsevier (1990)","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"36_CR24","unstructured":"Wang, T., Ba, J.: Exploring model-based planning with policy networks. arXiv preprint arXiv:1906.08649 (2019)"},{"key":"36_CR25","unstructured":"Feinberg, V., Wan, A., Stoica, I., Jordan, M.I., Gonzalez, J.E., Levine, S.: Model-based value estimation for efficient model-free reinforcement learning. arXiv preprint arXiv:1803.00101 (2018)"},{"key":"36_CR26","unstructured":"Clavera, I., Fu, V., Abbeel, P.: Model-augmented actor-critic: Backpropagating through paths. In: International Conference on Learning Representations (2020)"},{"key":"36_CR27","unstructured":"Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: model-based policy optimization. In: Advances in Neural Information Processing Systems, pp. 12498\u201312509 (2019)"},{"key":"36_CR28","unstructured":"Rajeswaran, A., Mordatch, I., Kumar, V.: A game theoretic framework for model based reinforcement learning. In: International Conference on Machine Learning, pp. 7953\u20137963. PMLR (2020)"},{"key":"36_CR29","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961\u20132970. PMLR (2019)"},{"key":"36_CR30","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"36_CR31","unstructured":"Du, Y., Han, L., Fang, M., Liu, J., Dai, T., Tao, D.: Liir: learning individual intrinsic reward in multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 4403\u20134414 (2019)"},{"key":"36_CR32","unstructured":"Wang, T., Dong, H., Lesser, V., Zhang, C.: Roma: multi-agent reinforcement learning with emergent roles. In: International Conference on Machine Learning, pp. 9876\u20139886 (2020)"},{"issue":"9","key":"36_CR33","doi-asserted-by":"publisher","first-page":"e0222215","DOI":"10.1371\/journal.pone.0222215","volume":"14","author":"YJ Park","year":"2019","unstructured":"Park, Y.J., Cho, Y.S., Kim, S.B.: Multi-agent reinforcement learning with approximate model learning for competitive games. PLoS ONE 14(9), e0222215 (2019)","journal-title":"PLoS ONE"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, W., Wang, X., Shen, J., Zhou, M.: Model-based multi-agent policy optimization with adaptive opponent-wise rollouts. arXiv preprint arXiv:2105.03363 (2021)","DOI":"10.24963\/ijcai.2021\/466"},{"key":"36_CR35","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008\u20131014 (2000)"},{"key":"36_CR36","unstructured":"Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization. In: International Conference on Learning Representations (2018)"},{"key":"36_CR37","unstructured":"D\u2019Oro, P., Ja\u015bkowski, W.: How to learn a useful critic? Model-based action-gradient-estimator policy optimization. In: Advances in Neural Information Processing Systems, pp. 313\u2013324 (2020)"},{"key":"36_CR38","unstructured":"Sukhbaatar, S., Fergus, R., et al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, pp. 2244\u20132252 (2016)"},{"key":"36_CR39","unstructured":"Wang, T., Wang, J., Wu, Y., Zhang, C.: Influence-based multi-agent exploration. In: International Conference on Learning Representations (2019)"},{"key":"36_CR40","unstructured":"He, H., Boyd-Graber, J., Kwok, K., Daum\u00e9 III, H.: Opponent modeling in deep reinforcement learning. In: International Conference on Machine Learning, pp. 1804\u20131813. PMLR (2016)"},{"key":"36_CR41","unstructured":"Vaswani, A., et al.:. Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"36_CR42","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, pp. 2974\u20132982 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"36_CR43","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 2186\u20132188 (2019)"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-96772-7_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T06:50:29Z","timestamp":1674975029000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-96772-7_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030967710","9783030967727"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-96772-7_36","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":"16 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2021","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":"pdcat2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/cse.sysu.edu.cn\/pdcat2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"97","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":"24","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":"34","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":"25% - 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","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}