{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:53:15Z","timestamp":1730292795716,"version":"3.28.0"},"reference-count":8,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,12]]},"DOI":"10.1109\/robio.2007.4522470","type":"proceedings-article","created":{"date-parts":[[2008,5,21]],"date-time":"2008-05-21T15:51:43Z","timestamp":1211385103000},"page":"1978-1982","source":"Crossref","is-referenced-by-count":0,"title":["A unifying framework for HAMs-family HRL methods"],"prefix":"10.1109","author":[{"given":"Du","family":"Xiaoqin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Qinghua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Jianjun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","first-page":"227","volume":"13","author":"dietterich","year":"2000","journal-title":"Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1016\/S0004-3702(99)00052-1"},{"year":"2004","author":"ravindran","journal-title":"An Algebraic Approach to Abstraction in Reinforcement Learning Doctoral Dissertation Department of Computer Science","key":"ref6"},{"year":"2003","author":"andre","journal-title":"Programmable Reinforcement Learning Agents","key":"ref5"},{"year":"2005","author":"ghavamzadeh","journal-title":"Hierarchical Reinforcement Learning in Continuous State and Multi-Agent Environments","key":"ref8"},{"key":"ref7","article-title":"Hierarchical Optimization of Policy-Coupled Semi-Markov Decision Processes","author":"wang","year":"1999","journal-title":"Proceedings of the 16th International Conference on Machine Learning (ICML '99)"},{"year":"1998","author":"hierarchical","journal-title":"Learning for Markov Decision Processes","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1023\/A:1022140919877"}],"event":{"name":"2007 IEEE International Conference on Robotics and biomimetics (ROBIO)","start":{"date-parts":[[2007,12,15]]},"location":"Sanya, China","end":{"date-parts":[[2007,12,18]]}},"container-title":["2007 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4510710\/4522117\/04522470.pdf?arnumber=4522470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T14:24:57Z","timestamp":1489674297000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4522470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,12]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/robio.2007.4522470","relation":{},"subject":[],"published":{"date-parts":[[2007,12]]}}}