{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T22:07:30Z","timestamp":1725746850012},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,1]]},"DOI":"10.1109\/cloudnet59005.2023.10490082","type":"proceedings-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T17:51:58Z","timestamp":1712685118000},"page":"247-255","source":"Crossref","is-referenced-by-count":0,"title":["RoMA: Resilient Multi-Agent Reinforcement Learning with Dynamic Participating Agents"],"prefix":"10.1109","author":[{"given":"Xuting","family":"Tang","sequence":"first","affiliation":[{"name":"Stevens Institute of Technology,Computer Science Department,Hoboken,USA"}]},{"given":"Jia","family":"Xu","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology,Computer Science Department,Hoboken,USA"}]},{"given":"Shusen","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3232390"},{"key":"ref3","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"Bahdanau","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Rashid"},{"key":"ref9","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Iqbal"},{"key":"ref10","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Iqbal"},{"key":"ref11","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","volume-title":"International Conference on Machine Learning","author":"Liu"},{"article-title":"Updet: Universal multi-agent rl via policy decoupling with transformers","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7529"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6196"},{"key":"ref15","first-page":"8776","article-title":"Towards open ad hoc teamwork using graph-based policy learning","volume-title":"International Conference on Machine Learning","author":"Rahman"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","year":"2019","author":"Ackermann","key":"ref18"},{"key":"ref19","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref21"}],"event":{"name":"2023 IEEE 12th International Conference on Cloud Networking (CloudNet)","start":{"date-parts":[[2023,11,1]]},"location":"Hoboken, NJ, USA","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 IEEE 12th International Conference on Cloud Networking (CloudNet)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10490006\/10490015\/10490082.pdf?arnumber=10490082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T06:08:11Z","timestamp":1712729291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10490082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cloudnet59005.2023.10490082","relation":{},"subject":[],"published":{"date-parts":[[2023,11,1]]}}}