{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T13:49:47Z","timestamp":1730296187533,"version":"3.28.0"},"reference-count":10,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020,1]]},"DOI":"10.1109\/sii46433.2020.9026225","type":"proceedings-article","created":{"date-parts":[[2020,3,10]],"date-time":"2020-03-10T02:14:57Z","timestamp":1583806497000},"page":"201-204","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Method with Internal World Model Training"],"prefix":"10.1109","author":[{"given":"Kenji","family":"Hirata","sequence":"first","affiliation":[]},{"given":"Hiroyuki","family":"Iizuka","sequence":"additional","affiliation":[]},{"given":"Masahito","family":"Yamamoto","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","first-page":"1928","author":"mnih","year":"2016","journal-title":"Asynchronous methods for deep reinforcement learning In International conference on machine learning"},{"key":"ref3","first-page":"529","volume":"5187540","author":"mnih","year":"2015","journal-title":"Human-level control through deep reinforcement learning Nature 518"},{"key":"ref10","article-title":"Learning to Predict Without Looking Ahead: World Models Without Forward Prediction","author":"freeman","year":"2019","journal-title":"arXiv preprint arXiv 1910 13038"},{"key":"ref6","first-page":"1233","volume":"198","author":"tanaka","year":"2006","journal-title":"Brain mechanism of reward prediction under predictable and unpredictable environmental dynamics Neural Networks"},{"key":"ref5","first-page":"354","volume":"5507676","author":"silver","year":"2017","journal-title":"Mastering the game of go without human knowledge"},{"key":"ref8","article-title":"Stochastic video generation with a learned prior","author":"denton","year":"2018","journal-title":"arXiv preprint arXiv 1802 07814"},{"key":"ref7","article-title":"Learning and querying fast generative models for reinforcement learning","author":"buesing","year":"2018","journal-title":"arXiv preprint arXiv 1802 03395"},{"journal-title":"Playing atari with deep reinforcement learning arXiv preprint arXiv 13125602","year":"2013","author":"mnih","key":"ref2"},{"journal-title":"World models arXiv preprint arXiv 180310122","year":"2018","author":"ha","key":"ref9"},{"journal-title":"Proximal policy optimization algorithms arXiv preprint arXiv 170706347","year":"2017","author":"schulman","key":"ref1"}],"event":{"name":"2020 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2020,1,12]]},"location":"Honolulu, HI, USA","end":{"date-parts":[[2020,1,15]]}},"container-title":["2020 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9011449\/9025808\/09026225.pdf?arnumber=9026225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T11:14:39Z","timestamp":1656587679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9026225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/sii46433.2020.9026225","relation":{},"subject":[],"published":{"date-parts":[[2020,1]]}}}