{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:32:25Z","timestamp":1763202745637,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"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":[[2022,12,9]]},"DOI":"10.1109\/raai56146.2022.10092972","type":"proceedings-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T15:02:31Z","timestamp":1681138951000},"page":"74-79","source":"Crossref","is-referenced-by-count":1,"title":["Reward Shaping Study for Sub-Goal Based Robotic Tasks"],"prefix":"10.1109","author":[{"given":"Liliana","family":"Ant\u00e3o","sequence":"first","affiliation":[{"name":"University of Porto Rua Dr. Roberto Frias,Research Center for Systems and Technologies Faculty of Engineering,Porto,Portugal,4200-465"}]},{"given":"Leonor","family":"Santos","sequence":"additional","affiliation":[{"name":"University of Porto Rua Dr. Roberto Frias,Research Center for Systems and Technologies Faculty of Engineering,Porto,Portugal,4200-465"}]},{"given":"Jo\u00e3o","family":"Reis","sequence":"additional","affiliation":[{"name":"University of Porto Rua Dr. Roberto Frias,Research Center for Systems and Technologies Faculty of Engineering,Porto,Portugal,4200-465"}]},{"given":"Gil","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"University of Porto Rua Dr. Roberto Frias,Research Center for Systems and Technologies Faculty of Engineering,Porto,Portugal,4200-465"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340956"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090364"},{"key":"ref14","first-page":"4565","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Ad- vances in neural information processing systems"},{"key":"ref11","first-page":"8411","article-title":"Learning from trajectories via subgoal discovery","volume":"32","author":"paul","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"1409","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","author":"li","year":"2019","journal-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103711"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/OJIES.2020.3031660"},{"key":"ref8","article-title":"Hirl: Hierarchical inverse reinforcement learning for long-horizon tasks with delayed rewards","author":"krishnan","year":"2016","journal-title":"arXiv preprint arXiv 1604 06508"},{"key":"ref7","article-title":"Potential based reward shaping for hierarchical re- inforcement learning","author":"gao","year":"2015","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"ref9","first-page":"1613","article-title":"Online learning of shaping reward with sub- goal knowledge","author":"okudo","year":"2021","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref4","article-title":"Reinforcement learning and the reward engineering princi- ple","author":"dewey","year":"2014","journal-title":"2014 AAAI Spring Symposium Series"},{"key":"ref3","first-page":"1","article-title":"Modeling robot assembly tasks in manufacturing using sysml","author":"huckaby","year":"2014","journal-title":"ISR\/Robotik 2014 41st International Symposium on Robotics"},{"key":"ref6","article-title":"Reward engineering for object pick and place training","author":"nagpal","year":"2020","journal-title":"arXiv preprint arXiv 2001 04933"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/331"}],"event":{"name":"2022 2nd International Conference on Robotics, Automation and Artificial Intelligence (RAAI)","start":{"date-parts":[[2022,12,9]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,11]]}},"container-title":["2022 2nd International Conference on Robotics, Automation and Artificial Intelligence (RAAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10092949\/10092953\/10092972.pdf?arnumber=10092972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T14:22:41Z","timestamp":1682950961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10092972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,9]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/raai56146.2022.10092972","relation":{},"subject":[],"published":{"date-parts":[[2022,12,9]]}}}