{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:31:40Z","timestamp":1763202700114,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2047064,2047010,1947419,1947418"],"award-info":[{"award-number":["2047064,2047010,1947419,1947418"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891898","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Virtual-Agent Reinforcement Learning for a Stochastic Predator-Prey Grid Environment"],"prefix":"10.1109","author":[{"given":"Yanbin","family":"Lin","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Ni","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science Florida Atlantic University,Boca Raton,FL,USA,33431"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Multi-agent reinforcement learning in sequential social dilemmas","author":"leibo","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Transfer learning in multi-agent reinforcement learning with double q-networks for distributed resource sharing in v2x communication","author":"zafar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep rein-forcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM41954.2020.9281629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM40551.2019.8973423"},{"journal-title":"Competition between reinforcement learning methods in a predator-prey grid world","year":"2008","author":"schrum","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecocom.2020.100815"},{"key":"ref17","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"5143","article-title":"Competitive multi-agent inverse reinforcement learning with sub-optimal demonstrations","author":"wang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/AEEES48850.2020.9121512"},{"key":"ref8","first-page":"6","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280475"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1109\/TNNLS.2013.2271454","article-title":"Goal representation heuristic dynamic programming on maze navigation","volume":"24","author":"ni","year":"2013","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849368"},{"key":"ref21","first-page":"2613","article-title":"Double q-learning","volume":"23","author":"hasselt","year":"2010","journal-title":"Advances in Neural Information Pro-cessing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891898.pdf?arnumber=9891898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:57:03Z","timestamp":1667516223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891898","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}