{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:22:42Z","timestamp":1777486962841,"version":"3.51.4"},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/robio.2018.8665165","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T20:01:56Z","timestamp":1552939316000},"page":"886-891","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Robot Cooperation Strategy in Game Environment Using Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hongda","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Decai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Conterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)"},{"key":"ref11","author":"jaderberg","year":"2018","journal-title":"Human-level performance in first-person multiplayer games with population-based deen reinforcement learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460180"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963532"},{"key":"ref15","first-page":"3204","article-title":"An investigation of guarding a territory problem in a grid world","author":"lu","year":"2010","journal-title":"American Control Conference (ACC)"},{"key":"ref4","author":"vinyals","year":"2017","journal-title":"Starcraft ii A new challenge for reinforcement learning"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2015","journal-title":"Nature"},{"key":"ref6","author":"peng","year":"2017","journal-title":"Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games"},{"key":"ref5","author":"sukhbaatar","year":"2016","journal-title":"Learning multiagent communication with backpropagation"},{"key":"ref8","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"ICML 2017 Proceedings of the Thirty-Fourth International Conference on Machine Learning"},{"key":"ref7","author":"usunier","year":"2016","journal-title":"Episodic exploration for deep deterministic policies An application to starcraft micromanagement tasks"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","volume":"26","author":"mnih","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"A unified game-throretic approach to multiagent reinforcement learning","author":"lanctot","year":"2017","journal-title":"The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS)"}],"event":{"name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2018,12,12]]},"end":{"date-parts":[[2018,12,15]]}},"container-title":["2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8653250\/8664715\/08665165.pdf?arnumber=8665165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:05:08Z","timestamp":1598231108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8665165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/robio.2018.8665165","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}