{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T15:16:49Z","timestamp":1778426209770,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/iros.2017.8206505","type":"proceedings-article","created":{"date-parts":[[2017,12,14]],"date-time":"2017-12-14T17:12:59Z","timestamp":1513271579000},"page":"6059-6066","source":"Crossref","is-referenced-by-count":73,"title":["Combining neural networks and tree search for task and motion planning in challenging environments"],"prefix":"10.1109","author":[{"given":"Chris","family":"Paxton","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasumathi","family":"Raman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory D.","family":"Hager","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marin","family":"Kobilarov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"gu","year":"2016","journal-title":"Continuous deep q-learning with model-based acceleration"},{"key":"ref11","first-page":"3338","article-title":"Deep learning for real-time atari game play using offline monte-carlo tree search planning","author":"xiaoxiao","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","article-title":"Reinforcement learning in robotics: A survey","volume":"32","author":"jens","year":"2013","journal-title":"I J Robotics Res"},{"key":"ref13","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref14","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref15","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-150682"},{"key":"ref17","author":"plappert","year":"2016","journal-title":"keras-rl"},{"key":"ref18","article-title":"Sorry dave, i'm afraid i can't do that: Explaining unachievable robot tasks using natural language","author":"vasumathi","year":"2013","journal-title":"Robotics Science and Systems (RSS)"},{"key":"ref19","author":"shalev-shwartz","year":"2016","journal-title":"Safe Multi-Agent Reinforcement Learning for Autonomous Driving"},{"key":"ref4","author":"bojarski","year":"2016","journal-title":"End to End Learning for Self-Driving Cars"},{"key":"ref3","article-title":"Linear encodings of bounded LTL model checking","volume":"2","author":"armin","year":"2006","journal-title":"Logical Methods in Computer Science"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-044450813-3\/50026-6"},{"key":"ref5","author":"keras","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref7","first-page":"19","article-title":"Continuous rapid action value estimates","volume":"20","author":"couetoux","year":"2011","journal-title":"The 3rd Asian Conference on Machine Learning (ACML 2011)"},{"key":"ref2","author":"bellman","year":"1967","journal-title":"Introduction to the mathematical theory of control processes \/ Richard Bellman"},{"key":"ref1","author":"andreas","year":"2016","journal-title":"Modular multitask reinforcement learning with policy sketches"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref20","author":"vikas","year":"2014","journal-title":"Towards integrating hierarchical goal networks and motion planners to support planning for human-robot teams"},{"key":"ref22","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","author":"toussaint","year":"2015","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"david","year":"2016","journal-title":"Nature"},{"key":"ref24","article-title":"Monte carlo tree search in continuous action spaces with execution uncertainty","author":"yee","year":"2016","journal-title":"IJCAI"},{"key":"ref23","author":"xu","year":"2016","journal-title":"End-to-end Learning of Driving Models from Large-scale Video Datasets"}],"event":{"name":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Vancouver, BC","start":{"date-parts":[[2017,9,24]]},"end":{"date-parts":[[2017,9,28]]}},"container-title":["2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8119304\/8202121\/08206505.pdf?arnumber=8206505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,7]],"date-time":"2019-10-07T21:51:20Z","timestamp":1570485080000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8206505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iros.2017.8206505","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}