{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T22:31:13Z","timestamp":1725748273006},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"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":[[2019,2]]},"DOI":"10.1109\/bigcomp.2019.8679366","type":"proceedings-article","created":{"date-parts":[[2019,4,5]],"date-time":"2019-04-05T03:03:38Z","timestamp":1554433418000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Accelerating Deep Reinforcement Learning Using Human Demonstration Data Based on Dual Replay Buffer Management and Online Frame Skipping"],"prefix":"10.1109","author":[{"given":"Sangho","family":"Yeo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangyoon","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","year":"2017","author":"perez","key":"ref10"},{"journal-title":"Dynamic frame skip deep q network","year":"2016","author":"lakshminarayanan","key":"ref11"},{"journal-title":"The atari grand challenge dataset","year":"2017","author":"kurin","key":"ref12"},{"journal-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","year":"2017","author":"vecer\u00edk","key":"ref13"},{"journal-title":"Reinforcement learning with deep energy-based policies","year":"2017","author":"haarnoja","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"journal-title":"Learning to repeat Fine grained action repetition for deep reinforcement learning","year":"2017","author":"sharma","key":"ref16"},{"journal-title":"Trust region policy optimization","year":"2015","author":"schulman","key":"ref17"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref18"},{"journal-title":"OpenAI Baselines","year":"2017","author":"dhariwal","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"journal-title":"Third-person imitation learning","year":"2017","author":"stadie","key":"ref3"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"journal-title":"End to End Learning for Self-Driving Cars","year":"2016","author":"bojarski","key":"ref5"},{"journal-title":"Reinforcement learning from imperfect demonstrations","year":"2018","author":"gao","key":"ref8"},{"journal-title":"Deep Q-learning from Demonstrations","year":"2017","author":"hester","key":"ref7"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"journal-title":"The Arcade Learning Environment An Evaluation Platform for General Agents","year":"2012","author":"bellemare","key":"ref9"},{"journal-title":"Distributed prioritized experience replay","year":"2018","author":"horgan","key":"ref20"}],"event":{"name":"2019 IEEE International Conference on Big Data and Smart Computing (BigComp)","start":{"date-parts":[[2019,2,27]]},"location":"Kyoto, Japan","end":{"date-parts":[[2019,3,2]]}},"container-title":["2019 IEEE International Conference on Big Data and Smart Computing (BigComp)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671661\/8678915\/08679366.pdf?arnumber=8679366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:11:09Z","timestamp":1657854669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8679366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/bigcomp.2019.8679366","relation":{},"subject":[],"published":{"date-parts":[[2019,2]]}}}