{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:44:45Z","timestamp":1730270685102,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8593728","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Accelerating Goal-Directed Reinforcement Learning by Model Characterization"],"prefix":"10.1109","author":[{"given":"Shoubhik","family":"Debnath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav","family":"Sukhatme","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lantao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"RViz 3D visualization tool for ROS","year":"0","key":"ref30"},{"key":"ref10","first-page":"24","author":"craig","year":"1998","journal-title":"Structured reachability analysis for markov decision processes In Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence"},{"journal-title":"Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning ArXiv e-prints","year":"2017","author":"chebotar","key":"ref11"},{"journal-title":"MBMF Model-Based Priors for Model-Free Reinforcement Learning ArXiv e-prints","year":"2017","author":"bansal","key":"ref12"},{"key":"ref13","first-page":"216","author":"sutton","year":"1990","journal-title":"Integrated architectures for learning planning and reacting based on approximating dynamic programming In In Proceedings of the Seventh International Conference on Machine Learning"},{"key":"ref14","first-page":"353","author":"sutton","year":"1991","journal-title":"Planning by incremental dynamic programming In In Proceedings of the Eighth International Workshop on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942746"},{"journal-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","year":"2017","author":"nagabandi","key":"ref16"},{"journal-title":"Task-based End-to-end Model Learning in Stochastic Optimization ArXiv e-prints","year":"2017","author":"donti","key":"ref17"},{"journal-title":"Goal-Driven Dynamics Learning via Bayesian Optimization ArXiv e-prints","year":"2017","author":"bansal","key":"ref18"},{"journal-title":"Finite Mathematical Structures","year":"1959","author":"kemeny","key":"ref19"},{"key":"ref28","first-page":"996","author":"kearns","year":"1999","journal-title":"Finite-sample convergence rates for q-learning and indirect algorithms In Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems II"},{"journal-title":"Trust Region Policy Optimization ArXiv e-prints","year":"2015","author":"schulman","key":"ref4"},{"key":"ref27","first-page":"49","volume":"121","author":"boutilier","year":"2000","journal-title":"Stochastic dynamic programming with factored representations Artificial intelligence"},{"key":"ref3","first-page":"1238","volume":"32","author":"jens","year":"2013","journal-title":"Reinforcement learning in robotics A survey The International Journal of Robotics Research"},{"key":"ref6","first-page":"45","volume":"7","author":"whitehead","year":"1991","journal-title":"Learning to perceive and act by trial and error Machine Learning"},{"key":"ref29","first-page":"1061","author":"cobo","year":"2013","journal-title":"Object focused q-earning for autonomous agents In Proceedings of the 2013 International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref5","first-page":"1","volume":"2","author":"deisenroth","year":"2013","journal-title":"A Survey on Policy Search for Robotics ser Foundations and trends in robotics"},{"journal-title":"On-line q-learning using connectionist systems Technical report","year":"1994","author":"rummery","key":"ref8"},{"key":"ref7","first-page":"279","author":"watkins","year":"1992","journal-title":"Q-learning Mach Learn"},{"key":"ref2","first-page":"227","volume":"22","author":"koenig","year":"1996","journal-title":"The Effect of Representation and Knowledge on Goal-Directed Exploration with Reinforcement-Learning Algorithms"},{"journal-title":"Reachability and differential based heuristics for solving markov decision processes In Proceedings of 2017 International Symposium on Robotics Research forthcoming","year":"0","author":"debnath","key":"ref9"},{"key":"ref1","first-page":"131","author":"de s braga","year":"1998","journal-title":"Goal-directed reinforcement learning using variable learning rate In Flavio Moreira de Oliveira editor Advances in Artificial Intelligence"},{"key":"ref20","first-page":"103","author":"moore","year":"1993","journal-title":"Prioritized sweeping Reinforcement learning with less data and less time In Machine Learning"},{"key":"ref22","first-page":"851","volume":"6","author":"wingate","year":"2005","journal-title":"Prioritization methods for accelerating mdp solvers Journal of Machine Learning Research"},{"journal-title":"Generalized prioritized sweeping Advances in Neural Information Processing Systems","year":"1998","author":"andre","key":"ref21"},{"key":"ref24","first-page":"9","volume":"3","author":"sutton","year":"1988","journal-title":"Learning to predict by the methods of temporal difference Machine Learning"},{"key":"ref23","first-page":"237","volume":"4","author":"pack kaelbling","year":"1996","journal-title":"Reinforcement learning A survey J Artif Int Res"},{"journal-title":"Matrix Computations","year":"1996","author":"golub","key":"ref26"},{"key":"ref25","first-page":"185","volume":"22","author":"assaf","year":"1985","journal-title":"First-passage times with pfr densities Journal of Applied Probability"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2018,10,1]]},"location":"Madrid","end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08593728.pdf?arnumber=8593728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:51:43Z","timestamp":1598248303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8593728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8593728","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}