{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:37:36Z","timestamp":1761176256511,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Multi-agent reinforcement learning has achieved substantial progress under the centralized training with decentralized execution framework. However, most existing methods assume deterministic and noise-free local observations, limiting applicability to real-world environments characterized by stochastic partial observability. This paper introduces GraphSem, a semantic-graph communication framework designed to enhance agent coordination under observation uncertainty and randomized initial conditions. Graph-Sem employs Transformer-based encoders to abstract higher-level features from observations, selectively transmits these features via dynamic communication weighting, and fuses inter-agent information through an attention-guided graph convolutional network. To approximate aspects of real-world sensing challenges, we introduce controlled stochasticity to both observations and initial states during training. Experiments on perturbed variants of SMAC and Traffic Junction benchmarks show that GraphSem outperforms state-of-the-art baselines across diverse coordination tasks, with improvements of up to 30.4% in average win rates. Ablation studies suggest that semantic encoding, graph-based message fusion, and adaptive communication mechanisms collectively contribute to enhanced robustness, sample efficiency, and performance under stochastic conditions.<\/jats:p>","DOI":"10.3233\/faia251266","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:56:27Z","timestamp":1761126987000},"source":"Crossref","is-referenced-by-count":0,"title":["GraphSem: Robust Multi-Agent Reinforcement Learning via Semantic-Graph Communication"],"prefix":"10.3233","author":[{"given":"Zaipeng","family":"Xie","sequence":"first","affiliation":[{"name":"Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China"},{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"given":"Yaowu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"given":"Sitong","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"given":"Jianan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:56:28Z","timestamp":1761126988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251266","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}