{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:59:32Z","timestamp":1780502372088,"version":"3.54.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802681","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"541-548","source":"Crossref","is-referenced-by-count":7,"title":["Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Shaunak A.","family":"Mehta","sequence":"first","affiliation":[{"name":"Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soheil","family":"Habibian","sequence":"additional","affiliation":[{"name":"Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan P.","family":"Losey","sequence":"additional","affiliation":[{"name":"Virginia Tech,Collaborative Robotics Lab (Collab),Dept. of Mechanical Engineering,Blacksburg,VA,24061"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"HYDRA: Hybrid robot actions for imitation learning","volume-title":"Conference on Robot Learning","author":"Belkhale"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0160-0"},{"key":"ref3","article-title":"Waypoint-based imitation learning for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shi"},{"key":"ref4","volume-title":"Robot Modeling and Control","author":"Spong","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_81"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref9","article-title":"Data-efficient hierarchical reinforcement learning","author":"Nachum","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref11","article-title":"Hierarchical reinforcement learning by discovering intrinsic options","volume-title":"International Conference on Learning Representations","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref13","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","author":"Eysenbach","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3071062"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561315"},{"key":"ref16","article-title":"Motion planner augmented reinforcement learning for robot manipulation in obstructed environments","volume-title":"Conference on Robot Learning","author":"Yamada"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834710"},{"key":"ref18","article-title":"Why is posterior sampling better than optimism for reinforcement learning?","volume-title":"International Conference on Machine Learning","author":"Osband"},{"key":"ref19","article-title":"An analysis of ensemble sampling","author":"Qin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref21","article-title":"On lower bounds for regret in reinforcement learning","author":"Osband","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref24","article-title":"Episodic reinforcement learning in finite mdps: Minimax lower bounds revisited","author":"Domingues","year":"2021","journal-title":"Algorithmic Learning Theory"},{"key":"ref25","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref26","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802681.pdf?arnumber=10802681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:32:57Z","timestamp":1735198377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802681","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}