{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:39:57Z","timestamp":1730201997737,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"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":[[2020,9]]},"DOI":"10.1109\/cacre50138.2020.9230273","type":"proceedings-article","created":{"date-parts":[[2020,10,22]],"date-time":"2020-10-22T20:10:16Z","timestamp":1603397416000},"page":"697-701","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Modulate Action of Deterministic Policy for Autonomous Navigation"],"prefix":"10.1109","author":[{"given":"Xin","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref12","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2016","journal-title":"arXiv 1611 03673"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref13"},{"key":"ref14","article-title":"Deterministic Policy Gradient Algorithms","author":"david","year":"2014","journal-title":"31st International Conference on Machine Learning"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref16","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref18","first-page":"293","article-title":"Rapidly-exploring random trees: Progress and prospects","author":"lavalle","year":"2001","journal-title":"Algorithmic and Computational Robotics New Directions"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/RISSP.2003.1285562","article-title":"Optimal Path Planning for Mobile Robots Based on Intensified Ant Colony Optimization Algorithm","volume":"1","author":"fan","year":"2003","journal-title":"IEEE International Conference on Robotics Intelligent Systems and Signal Processing Proceedings"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","article-title":"Dota 2 with Large Scale Deep Reinforcement Learning","author":"berner","year":"2019","journal-title":"arXiv 1912 06680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011206"},{"key":"ref2","first-page":"1221","article-title":"Genetic algorithm based path planning for a mobile robot","volume":"1","author":"tu","year":"2003","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/7.869506"},{"key":"ref9","first-page":"2419","article-title":"Learning to navigate in cities without a map","author":"mirowski","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)","start":{"date-parts":[[2020,9,19]]},"location":"Dalian, China","end":{"date-parts":[[2020,9,20]]}},"container-title":["2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9229471\/9229898\/09230273.pdf?arnumber=9230273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:58:50Z","timestamp":1656345530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9230273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/cacre50138.2020.9230273","relation":{},"subject":[],"published":{"date-parts":[[2020,9]]}}}