{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:15:18Z","timestamp":1772554518320,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"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":[[2022,7,9]]},"DOI":"10.1109\/icarm54641.2022.9959550","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:31:50Z","timestamp":1669750310000},"page":"812-817","source":"Crossref","is-referenced-by-count":4,"title":["Manipulator Motion Planning via Centralized Training and Decentralized Execution Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuliu","family":"Wang","sequence":"first","affiliation":[{"name":"University of Tsukuba, 1-1-1 Tennodai,Intelligent and Mechanical Interaction System,Tsukuba,Ibaraki,Japan,305-8577"}]},{"given":"Ryusuke","family":"Sagawa","sequence":"additional","affiliation":[{"name":"Computer Vision Research Team, Artificial Intelligence Research Center(AIRC-CVRT), The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono,Tsukuba,Ibaraki,Japan,305-8577"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216774"},{"key":"ref13","first-page":"1180","author":"peters","year":"2008","journal-title":"Natural actor-critic Neurocomputing"},{"key":"ref14","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref16","article-title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","author":"yu","year":"2021","journal-title":"arXiv preprint arXiv 2103 05767"},{"key":"ref17","first-page":"6382","article-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"lowe","year":"2017","journal-title":"2017 31st International Conference on Neural Information Processing Systems"},{"key":"ref18","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref4","first-page":"1","article-title":"Decentralized reinforcement learning control of a robotic manipulator","author":"lucian","year":"2006","journal-title":"2006 9th International Conference on Control Automation Robotics and Vision"},{"key":"ref3","article-title":"Kochenderfer, Deep implicit coordination graphs for multi-agent reinforcement learning","author":"li","year":"2020","journal-title":"arXiv preprint arXiv 2006 11116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636477"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2016.7523669"},{"key":"ref8","first-page":"995","article-title":"RRT-connect: An efficient approach to singlequery path planning","volume":"2","author":"kuffner","year":"2000","journal-title":"Proceedings 2000 ICRA Millennium Conference IEEE International Conference on Robotics and Automation Symposia Proceedings (Cat No 00CH37065)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1095\/biolreprod56.2.328"},{"key":"ref2","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref1","first-page":"270","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref9","first-page":"1","article-title":"Multi-agent reinforcement learning: A survey","author":"lucian","year":"2006","journal-title":"2006 9th International Conference on Control Automation Robotics and Vision"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7471613"},{"key":"ref22","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref24","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref23","article-title":"Temporal difference models: Model-free deep RL for model-based control","author":"pong","year":"2018","journal-title":"arXiv preprint arXiv 1802 09085"}],"event":{"name":"2022 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Guilin, China","start":{"date-parts":[[2022,7,9]]},"end":{"date-parts":[[2022,7,11]]}},"container-title":["2022 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9959088\/9959097\/09959550.pdf?arnumber=9959550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:01:58Z","timestamp":1671480118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9959550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icarm54641.2022.9959550","relation":{},"subject":[],"published":{"date-parts":[[2022,7,9]]}}}