{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:28:54Z","timestamp":1767706134975,"version":"3.32.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"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":[[2024,9,2]]},"DOI":"10.1109\/pimrc59610.2024.10817200","type":"proceedings-article","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T19:22:36Z","timestamp":1735759356000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Transfer Learning With Less Negative Transfer for Multi-Agent Reinforcement Learning: Application and Evaluation in Base Station Control"],"prefix":"10.1109","author":[{"given":"Masanobu","family":"Namiki","sequence":"first","affiliation":[{"name":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"}]},{"given":"Yoshihiro","family":"Okawa","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"}]},{"given":"Natsuki","family":"Morita","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"}]},{"given":"Jun","family":"Kakuta","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"}]},{"given":"Masatoshi","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3096928"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CIS58238.2022.00018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.106004"},{"article-title":"Parameter space noise for exploration","volume-title":"International Conference on Learning Representations","author":"Plappert","key":"ref5"},{"key":"ref6","first-page":"1","article-title":"Transfer learning based parallel computation offloading scheme between mec servers in metro optical networks","volume-title":"2021 Asia Communications and Photonics Conference (ACP)","author":"Liu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2022-Spring54318.2022.9860707"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2016.027"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"113420","DOI":"10.1016\/j.eswa.2020.113420","article-title":"Decaf: Deep case-based policy inference for knowledge transfer in reinforcement learning","volume":"156","author":"Glatt","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3108237"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645556"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1615\/JMachLearnModelComput.2020034126"},{"issue":"1","key":"ref13","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. icml","volume":"30","author":"Maas"},{"key":"ref14","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"Clevert","year":"2015","journal-title":"arXiv preprint arXiv:1511.07289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref16","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"15032","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"34","author":"Terry","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2009.5208045"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2846694"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2015.55"},{"key":"ref21","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning.","author":"Achiam"}],"event":{"name":"2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","start":{"date-parts":[[2024,9,2]]},"location":"Valencia, Spain","end":{"date-parts":[[2024,9,5]]}},"container-title":["2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10817155\/10817156\/10817200.pdf?arnumber=10817200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T05:54:23Z","timestamp":1735797263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/pimrc59610.2024.10817200","relation":{},"subject":[],"published":{"date-parts":[[2024,9,2]]}}}