{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:33:12Z","timestamp":1774974792844,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206849","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-9","source":"Crossref","is-referenced-by-count":23,"title":["Adaptation of a wheel loader automatic bucket filling neural network using reinforcement learning"],"prefix":"10.1109","author":[{"given":"Siddharth","family":"Dadhich","sequence":"first","affiliation":[]},{"given":"Fredrik","family":"Sandin","sequence":"additional","affiliation":[]},{"given":"Ulf","family":"Bodin","sequence":"additional","affiliation":[]},{"given":"Ulf","family":"Andersson","sequence":"additional","affiliation":[]},{"given":"Torbjorn","family":"Martinsson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref38","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning"},{"key":"ref33","article-title":"Temporal credit assignment problem in reinforcement learning","author":"sutton","year":"1984","journal-title":"Ph D Dissertation"},{"key":"ref32","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proceedings of the 12th International Conference on Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61859-7_6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/2332510"},{"key":"ref36","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symp Operating Systems Design and Implementation (OSDI 16)"},{"key":"ref35","first-page":"565","article-title":"Reward shaping in episodic reinforcement learning","author":"grzes","year":"2017","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems"},{"key":"ref34","article-title":"Theory and application of reward shaping in reinforcement learning","author":"laud","year":"2004","journal-title":"Ph D Dissertation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21654"},{"key":"ref40","article-title":"How to discount deep reinforcement learning: Towards new dynamic strategies","author":"franc\u00b8ois-lavet","year":"2015","journal-title":"NIPS 2015 Workshop on Deep Reinforcement Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2004.832522"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574701003435"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.32832"},{"key":"ref15","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref16","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":"ref17","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv preprint arXiv 1712 01815"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref19","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF02497181"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18178\/ijeetc.7.4.178-182"},{"key":"ref3","article-title":"Learning and Reacting with Inaccurate Prediction: Applications to Autonomous Excavation","author":"maeda","year":"2013","journal-title":"Ph D Dissertation"},{"key":"ref6","first-page":"357","article-title":"A study to compare trajectory generation algorithms for automatic bucket filling in wheel loaders","author":"filla","year":"2014","journal-title":"3rd Commercial Vehicle Technology Symposium"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489388"},{"key":"ref5","article-title":"Automatic bucket fill","author":"almqvist","year":"2009","journal-title":"Master’s thesis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1308793"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2007.912709"},{"key":"ref2","first-page":"1","article-title":"On wheel loader fuel efficiency¨ difference due to operator behaviour distribution","author":"frank","year":"2012","journal-title":"Proceedings of the 2nd Commercial Vehicle Technology Symposium"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2005.1507293"},{"key":"ref1","article-title":"Dependability Assurance for Automatic Load Haul Dump Machines","author":"gustafson","year":"2011","journal-title":"Maintenance and Acoustics Division Department of Civil Environmental and Natural Resources Engineering Operation Lulea University of Technology Licentiate thesis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref21","article-title":"Learning to drive in a day","author":"kendall","year":"2018","journal-title":"arXiv preprint arXiv 1807 00412"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.04.010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3384\/ecp17144402"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2018.10.013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2016.7535925"},{"key":"ref25","article-title":"Automation and Traction Control of Articulated Vehicles","author":"andersson","year":"2013","journal-title":"Ph D Dissertation"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","location":"Glasgow, United Kingdom","start":{"date-parts":[[2020,7,19]]},"end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206849.pdf?arnumber=9206849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:54:07Z","timestamp":1656453247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206849","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}