{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T01:16:27Z","timestamp":1729646187736,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/cira.2003.1222154","type":"proceedings-article","created":{"date-parts":[[2004,3,2]],"date-time":"2004-03-02T02:26:50Z","timestamp":1078194410000},"page":"1120-1125","source":"Crossref","is-referenced-by-count":5,"title":["A study of reinforcement learning with knowledge sharing for distributed autonomous system"],"prefix":"10.1109","volume":"3","author":[{"given":"K.","family":"Ito","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Gofuku","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Y.","family":"Imoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Takeshita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"208","article-title":"Labeling Q-learning in hidden state environments","author":"lee","year":"2001","journal-title":"Proc of the 6th Int Symp on Artificial life and Robotics"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1016\/B978-1-55860-307-3.50030-7"},{"key":"ref12","first-page":"186","article-title":"Hierarchical optimal control of mdps","author":"mcgovern","year":"1998","journal-title":"Proc Yale Workshop Adaptive Learning Syst"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/3-540-62934-3_39","article-title":"A modular approach to multi-agent reinforcement learning","author":"ono","year":"1997","journal-title":"Distributed Artificial Intelligence Meets Machine Learning Learning in Multi-Agent Environments"},{"key":"ref14","first-page":"113","article-title":"Resolved motion rate control of a free-floating underwater robot with horizonal planar 2-link manipulator","author":"sagara","year":"2001","journal-title":"Proc of the 6th Int Symp on Artificial life and Robotics"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref15"},{"key":"ref16","first-page":"119","article-title":"Emergent systerns of motion patterns for locomotion robots","author":"svinin","year":"1999","journal-title":"Proc of Int Workshop on Emergent"},{"key":"ref17","first-page":"279","volume":"8","author":"watkins","year":"1992","journal-title":"Technical Note Q-Learning Machine Learning"},{"key":"ref18","first-page":"168","article-title":"Adaptive segmentation of the state space based on bayesian discrimination in reinforcement learning","author":"yamada","year":"2001","journal-title":"Proc of the 6th Int Symp on Artificial life and Robotics"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1527\/tjsai.16.510"},{"key":"ref3","first-page":"65","article-title":"Application of reinforcement learning to hyper-redundant system acquisition of locomotion pattern of snake like robot","author":"ito","year":"2001","journal-title":"Proc Pacific Asian Conf Intell Syst"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ROBOT.2002.1014235"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1527\/tjsai.17.363"},{"key":"ref8","first-page":"167","article-title":"Hierachical learning in stocastic domains","author":"kaelbling","year":"1993","journal-title":"Proceedings 10th International Conference on Machine Learning"},{"key":"ref7","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable markov decision problems","author":"jakkola","year":"1994","journal-title":"Advances of Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.7210\/jrsj.12.846"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/37.939943"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","author":"kaelbling","year":"1996","journal-title":"The Journal of Artificial Intelligence Research"}],"event":{"acronym":"CIRA-03","name":"2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation","location":"Kobe, Japan"},"container-title":["Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8660\/27453\/01222154.pdf?arnumber=1222154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T08:46:53Z","timestamp":1585644413000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1222154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/cira.2003.1222154","relation":{},"subject":[]}}