{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T15:05:28Z","timestamp":1760367928869,"version":"3.44.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T00:00:00Z","timestamp":1688256000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T00:00:00Z","timestamp":1688256000000},"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":[[2023,7,2]]},"DOI":"10.1109\/ssp53291.2023.10207979","type":"proceedings-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T13:24:22Z","timestamp":1691587462000},"page":"319-323","source":"Crossref","is-referenced-by-count":2,"title":["Semantic Communication for Partial Observation Multi-agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hoang Khoi","family":"Do","sequence":"first","affiliation":[{"name":"HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thi","family":"Quynh Dinh","sequence":"additional","affiliation":[{"name":"HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh Duong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Pusan National University,Department of Information Convergence Engineering,Pusan,Republic of Korea,46241"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tien","family":"Hoa Nguyen","sequence":"additional","affiliation":[{"name":"HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/RIVF55975.2022.10013868"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345353"},{"key":"ref3","article-title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","volume":"abs\/1610.03295","author":"Shalev-Shwartz","year":"2016","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Cooperative multi-agent reinforcement learning with partial observations","year":"2020","author":"Zhang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"article-title":"A survey of multi-agent reinforcement learning with communication","year":"2022","author":"Zhu","key":"ref7"},{"key":"ref8","article-title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","author":"Terry","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902846"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3135930"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946659"},{"article-title":"Rollout Sampling Policy Iteration for Decentralized POMDPs","volume-title":"Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, UAI 2010","author":"Wu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8260"},{"journal-title":"Monte-Carlo expectation maximization for decentralized POMDPs","year":"2013","author":"Wu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10135"},{"key":"ref16","first-page":"2011","article-title":"Stick-Breaking Policy Learning in Dec-POMDPs","volume-title":"Proceedings of the 24th International Conference on Artificial Intelligence","author":"Liu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/rs12223789"},{"article-title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","year":"2016","author":"Foerster","key":"ref18"},{"key":"ref19","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems","author":"Niu"},{"key":"ref20","first-page":"456","article-title":"Learning correlated communication topology in multi-agent reinforcement learning","volume-title":"Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems","author":"Du"},{"article-title":"TarMAC: Targeted multi-agent communication","year":"2019","author":"Das","key":"ref21"},{"key":"ref22","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Sukhbaatar"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref23"}],"event":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","start":{"date-parts":[[2023,7,2]]},"location":"Hanoi, Vietnam","end":{"date-parts":[[2023,7,5]]}},"container-title":["2023 IEEE Statistical Signal Processing Workshop (SSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10207925\/10207926\/10207979.pdf?arnumber=10207979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:33:42Z","timestamp":1758908022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10207979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,2]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ssp53291.2023.10207979","relation":{},"subject":[],"published":{"date-parts":[[2023,7,2]]}}}