{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:48:12Z","timestamp":1729676892473,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/humanoids.2018.8624949","type":"proceedings-article","created":{"date-parts":[[2019,1,25]],"date-time":"2019-01-25T02:51:38Z","timestamp":1548384698000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Learning Sequential Decision Tasks for Robot Manipulation with Abstract Markov Decision Processes and Demonstration-Guided Exploration"],"prefix":"10.1109","author":[{"given":"David","family":"Kent","sequence":"first","affiliation":[]},{"given":"Siddhartha","family":"Banerjee","sequence":"additional","affiliation":[]},{"given":"Sonia","family":"Chernova","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143928"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696474"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref14","first-page":"617","article-title":"Integrating reinforcement learning with human demonstrations of varying ability","author":"taylor","year":"2011","journal-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems- Volume 2 International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957788"},{"key":"ref16","first-page":"39","article-title":"The restaurant game: Learning social behavior and language from thousands of players online","volume":"3","author":"orkin","year":"2007","journal-title":"Journal of Game Development"},{"key":"ref17","first-page":"385","article-title":"Automatic learning and generation of social behavior from collective human gameplay","author":"orkin","year":"2009","journal-title":"Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 1 International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref18","article-title":"Online development of assistive robot behaviors for collaborative manipulation and human-robot teamwork","author":"hayes","year":"2014","journal-title":"Proceedings of the Machine Learning for Interactive Systems(MLIS) Workshop at AAAI"},{"key":"ref19","article-title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","author":"liu","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015384"},{"key":"ref3","first-page":"1003","article-title":"Generalizing plans to new environments in relational MDPs","author":"guestrin","year":"2003","journal-title":"Proceedings of the 18th International Joint Conference on Artificial Intelligence"},{"key":"ref6","first-page":"3675","article-title":"Hier-archical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref7","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v27i1.13867","article-title":"Planning with abstract Markov decision processes","author":"gopalan","year":"2017","journal-title":"ICAPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390187"},{"key":"ref9","first-page":"1726","article-title":"The Option-Critic Architecture","author":"bacon","year":"2017","journal-title":"AAAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451755"}],"event":{"name":"2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2018,11,6]]},"location":"Beijing, China","end":{"date-parts":[[2018,11,9]]}},"container-title":["2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8596719\/8624912\/08624949.pdf?arnumber=8624949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T09:43:17Z","timestamp":1720950197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8624949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2018.8624949","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}