{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:11:23Z","timestamp":1740100283498,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561607","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"9093-9100","source":"Crossref","is-referenced-by-count":0,"title":["Shaped Policy Search for Evolutionary Strategies using Waypoints"],"prefix":"10.1109","author":[{"given":"Kiran","family":"Lekkala","sequence":"first","affiliation":[{"name":"University of Southern California,ILab,Department of Computer Science,USA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Itti","sequence":"additional","affiliation":[{"name":"University of Southern California,ILab,Department of Computer Science, Psychology and NGP"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010750"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref12","first-page":"5420","article-title":"Adaptive Antithetic Sampling for Variance Reduction","volume":"97","author":"ren","year":"2019"},{"key":"ref13","first-page":"627","article-title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","volume":"15","author":"ross","year":"0"},{"journal-title":"The Cross Entropy Method A Unified Approach to Combinatorial Optimization Monte-Carlo Simulation (Information Science and Statistics)","year":"2004","author":"rubinstein","key":"ref14"},{"article-title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","year":"2017","author":"salimans","key":"ref15"},{"article-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"schulman","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref19","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"wierstra","year":"2014","journal-title":"J Mach Learn Res"},{"year":"2018","author":"gao","key":"ref4"},{"key":"ref3","first-page":"1","article-title":"CARLA: An Open Urban Driving Simulator","author":"dosovitskiy","year":"2017"},{"article-title":"A Visual Guide to Evolution Strategies","year":"2017","author":"ha","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013739"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/IROS45743.2020.9340956","article-title":"robo-gym - An Open Source Toolkit for Distributed Deep Reinforcement Learning on Real and Simulated Robots","author":"lucchi","year":"2020"},{"article-title":"The CMA Evolution Strategy: A Tutorial","year":"2016","author":"hansen","key":"ref7"},{"article-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref2"},{"key":"ref9","first-page":"4264","article-title":"Guided evolutionary strategies: augmenting random search with surrogate gradients","volume":"97","author":"maheswaranathan","year":"2019"},{"key":"ref1","first-page":"5048","article-title":"Hindsight Experience Replay","author":"andrychowicz","year":"2017"},{"article-title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","year":"0","author":"wijmans","key":"ref20"},{"article-title":"Sparse Allreduce: Efficient Scalable Communication for PowerLaw Data","year":"2013","author":"zhao","key":"ref21"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561607.pdf?arnumber=9561607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T19:08:58Z","timestamp":1674241738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561607","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}