{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:07Z","timestamp":1766061607082,"version":"3.48.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245885","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9760-9767","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized but Not Compromised: Modular Architecture with Refined Observation for Multi-Agent Model-Based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Shuqi","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027"}]},{"given":"Meiqin","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi’an,China,710049"}]},{"given":"Ronghao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027"}]},{"given":"Shanling","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027"}]},{"given":"Ping","family":"Wei","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi’an,China,710049"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid"},{"key":"ref2","first-page":"10 199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"381","article-title":"Scalable multi-agent model-based reinforcement learning","volume-title":"Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems","author":"Egorov"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26241"},{"key":"ref5","first-page":"281","article-title":"Aligning credit for multi-agent cooperation via model-based counterfactual imagination","volume-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems","author":"Chai"},{"key":"ref6","first-page":"72 904","article-title":"Facing off world model backbones: Rnns, transformers, and s4","volume":"36","author":"Deng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Sunehag"},{"key":"ref9","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","volume-title":"International Conference on machine learning","author":"Das"},{"article-title":"{RODE}: Learning roles to decompose multi-agent tasks","volume-title":"International Conference on Learning Representations","author":"Wang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref12"},{"key":"ref13","article-title":"Recurrent world models facilitate policy evolution","volume":"31","author":"Ha","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Mastering atari with discrete world models","volume-title":"International Conference on Learning Representations","author":"Hafner","key":"ref14"},{"article-title":"Mastering diverse domains through world models","year":"2023","author":"Hafner","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Transdreamer: Reinforcement learning with transformer world models","volume-title":"Deep RL Workshop NeurIPS 2021","author":"Chen","key":"ref17"},{"key":"ref18","first-page":"27 147","article-title":"Storm: Efficient stochastic transformer based world models for reinforcement learning","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Transformers are sample-efficient world models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Micheli","key":"ref19"},{"key":"ref20","article-title":"Neural discrete representation learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Bi-level latent variable model for sample-efficient multi-agent reinforcement learning","year":"2023","author":"Venugopal","key":"ref21"},{"article-title":"Decentralized transformers with centralized aggregation are sample-efficient multi-agent world models","year":"2024","author":"Zhang","key":"ref22"},{"key":"ref23","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Jaegle"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"article-title":"Harmonydream: Task harmonization inside world models","volume-title":"Forty-first International Conference on Machine Learning","author":"Ma","key":"ref25"},{"article-title":"Boosting multiagent reinforcement learning via permutation invariant and permutation equivariant networks","volume-title":"The Eleventh International Conference on Learning Representations","author":"HAO","key":"ref26"},{"key":"ref27","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems","author":"Samvelyan"},{"key":"ref28","first-page":"37 567","article-title":"Smacv2: An improved benchmark for cooperative multi-agent reinforcement learning","volume":"36","author":"Ellis","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245885.pdf?arnumber=11245885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:28Z","timestamp":1766061328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245885","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}