{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T11:11:44Z","timestamp":1766056304248,"version":"3.48.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247039","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"15262-15267","source":"Crossref","is-referenced-by-count":0,"title":["Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Linji","family":"Wang","sequence":"first","affiliation":[{"name":"George Mason University,Department of Computer Science"}]},{"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science"}]},{"given":"Yuanjie","family":"Lu","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science"}]},{"given":"Xuesu","family":"Xiao","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science"}]}],"member":"263","reference":[{"key":"ref1","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","volume":"99","author":"Ng","year":"1999"},{"key":"ref2","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341945"},{"article-title":"Grounded curriculum learning","year":"2024","author":"Wang","key":"ref4"},{"article-title":"Informativeness of reward functions in reinforcement learning","year":"2024","author":"Devidze","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3213466"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3322920"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2024.3427891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR50563.2020.9292572"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR53300.2021.9597689"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR62954.2024.10770034"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref17","first-page":"15 281","article-title":"Unpacking reward shaping: Understanding the benefits of reward engineering on sample complexity","volume":"35","author":"Gupta","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3561568"},{"key":"ref19","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"International conference on machine learning","author":"Riedmiller"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ssrr62954.2024.10770034"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2514\/1.G001921"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610079"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247039.pdf?arnumber=11247039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T11:06:15Z","timestamp":1766055975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247039","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}