references.bib

@InProceedings{atkeson1997, 
	author={C. G. Atkeson and J. C. Santamaria}, 
	booktitle={Proceedings of the IEEE International Conference on Robotics and Automation}, 
	series={ICRA'97},
	title={{A Comparison of Direct and Model-Based Reinforcement Learning}}, 
	month={April},
	year={1997}, 
	volume={4}, 
	pages={3557--3564}, 
	keywords={learning (artificial intelligence);model reference adaptive control systems;nonlinear control systems;robots;acrobot;direct reinforcement learning;model-based reinforcement learning;pendulum swing-up;Computational modeling;Control system synthesis;Control systems;Educational institutions;Force control;Jacobian matrices;Learning;Robots;State-space methods;Training data},
}

@incollection{bacciu2015probabilistic,
	title = {{Probabilistic Modeling in Machine Learning}},
	author = {D. Bacciu and P. J. G. Lisboa and A. Sperduti and T. Villmann},
	editor = {Kacprzyk, Janusz and Pedrycz, Witold},
	isbn = {978-3-662-43505-2},
	year = {2015},
	date = {2015-01-01},
	pages = {545--575},
	publisher = {Springer Berlin Heidelberg},
	address = {Berlin, Heidelberg},
	keywords = {Bayesian networks, generative model, graphical models, hidden Markov models},
	pubstate = {published},
	tppubtype = {incollection}
}

@inproceedings{baker1992large,
	title={{Large Vocabulary Recognition of Wall Street Journal Sentences at Dragon Systems}},
	author={Baker, James and Baker, Janet and Bamberg, Paul and Bishop, Kathleen and Gillick, Larry and Helman, Vera and Huang, Zezhen and Ito, Yoshiko and Lowe, Stephen and Peskin, Barbara and Roth, Robert and Scattone, Francesco},
	booktitle={Proceedings of the Workshop on Speech and Natural Language},
	pages={387--392},
	year={1992},
	organization={Association for Computational Linguistics},
	isbn = {1-55860-272-0}
}

@BOOK{barberBRML2012,
	author = {Barber, D.},
	title= {{Bayesian Reasoning and Machine Learning}},
	publisher = {{Cambridge University Press}},
	year = 2012}

@article{barto1995learning,
	title={{Learning to Act using Real-Time Dynamic Programming}},
	author={Barto, Andrew G. and Bradtke, Steven J. and Singh, Satinder P.},
	journal={Artificial intelligence},
	volume={72},
	number={1-2},
	pages={81--138},
	year={1995},
	publisher={Elsevier}
}

@inproceedings{bergstra2011algorithms,
	title={{Algorithms for Hyper-Parameter Optimization}},
	author={Bergstra, James S. and Bardenet, R{\'e}mi and Bengio, Yoshua and K{\'e}gl, Bal{\'a}zs},
	booktitle = {Proceedings of the 24th International Conference on Neural Information Processing Systems},
	series = {NIPS'11},
	pages={2546--2554},
	year={2011},
	isbn = {978-1-61839-599-3},
	publisher = {Curran Associates Inc.},
}

@INPROCEEDINGS{bhatia2010sampling, 
	author={A. Bhatia and L. E. Kavraki and M. Y. Vardi}, 
	booktitle={2010 IEEE International Conference on Robotics and Automation}, 
	title={{Sampling-Based Motion Planning with Temporal Goals}}, 
	year={2010}, 
	pages={2689-2696}, 
	keywords={mobile robots;path planning;temporal logic;discrete abstraction;geometry-based approach;low-level sampling-based planner;mobile robots;multilayered synergistic approach;propositions;sampling-based motion planning;second-order nonlinear robot models;temporal goals;temporal logic specifications;Computational geometry;Logic;Mobile robots;Motion planning;Robotics and automation;Sampling methods;Solid modeling;Sun;USA Councils;Vehicle dynamics},
	ISSN={1050-4729}, 
}

@article{bilmes1998gentle,
	title={{A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models}},
	author={Bilmes, Jeff A.},
	journal={International Computer Science Institute},
	volume={4},
	number={510},
	pages={126},
	year={1998}
}

@article{Boutilier1999,
	author = {Boutilier, Craig and Dean, Thomas and Hanks, Steve},
	isbn = {90-5199-237-8},
	issn = {10769757},
	journal = {Journal of Artificial Intelligence Research},
	pages = {1--94},
	title = {{Decision-Theoretic Planning: Structural Assumptions and Computational Leverage}},
	volume = {11},
	year = {1999}
}

@article{Brafman2002,
	author = {Brafman, Ronen I and Tennenholtz, Moshe},
	isbn = {1532-4435},
	issn = {15324435},
	journal = {Journal of Machine Learning Research},
	keywords = {decision processes,learning games,markov,provably efficient learning,reinforcement learning,stochastic games},
	mendeley-groups = {MDP Model Learning},
	pages = {213--231},
	title = {{R-MAX -- A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning}},
	volume = {3},
	year = {2002}
}

@article{Brochu2010_x,
	Author = {Eric Brochu and Vlad M. Cora and Nando {de Freitas}},
	  journal   = {CoRR},
	  volume    = {abs/1012.2599},
	title = {{A Tutorial on Bayesian Optimization of}\\ {Expensive} {Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning}},
	year = {2010}}
}

@techreport{Brochu2010,
	Author = {Eric Brochu and Vlad M. Cora and Nando {de Freitas}},
	Month = {December},
	Number = {arXiv:1012.2599},
	Title = {{A Tutorial on Bayesian Optimization of}\\ {Expensive} {Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning}},
	Type = {eprint},
	Year = {2010}}
}

@inproceedings{buffet2005robust,
	author = {Buffet, Olivier and Aberdeen, Douglas},
	title = {{Robust Planning with (L)RTDP}},
	booktitle = {Proceedings of the 19th International Joint Conference on Artificial Intelligence},
	series = {IJCAI'05},
	year = {2005},
	location = {Edinburgh, Scotland},
	pages = {1214--1219},
	numpages = {6},
	publisher = {Morgan Kaufmann Publishers Inc.},
	address = {San Francisco, CA, USA},
} 

@article{caelli2001shape,
	title={{Shape Tracking and Production using Hidden Markov Models}},
	author={Caelli, Terry and McCabe, Andrew and Briscoe, Garry},
	journal={International Journal of Pattern Recognition and Artificial Intelligence},
	volume={15},
	number={01},
	pages={197--221},
	year={2001},
	publisher={World Scientific}
}

@article{calinon2007learning,
	title={{On Learning, Representing, and Generalizing a Task in a Humanoid Robot}},
	author={Calinon, Sylvain and Guenter, Florent and Billard, Aude},
	journal={IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)},
	volume={37},
	number={2},
	pages={286--298},
	year={2007},
	publisher={IEEE}
}

@inproceedings{cassandra1998spa,
	author = {Cassandra, A. R.},
	booktitle = {{Working Notes of AAAI 1998 Fall Symposium on Planning with Partially Observable Markov Decision Processes}},
	comment = {* Good for ideas on how POMDPs could be used
	* Types of applications - machine maintenance, robot autonomy, etc. 
	* For robotic applications, control rules for robots done using models at higher level of abstraction than what robot actuators and sensors provide, or to do it at a hierarchical level. },
	pages = {17--24},
	title = {{A Survey of POMDP Applications}},
	year = {1998}
}

@article{chamie2015finite,
	title={{Finite-Horizon Markov Decision Processes with State Constraints}},
	author={Chamie, Mahmoud El and Açıkmeşe, Behçet},
	journal = {arXiv preprint arXiv:1507.01585},
	year={2015}
}

@inbook{chinaei2011,
	author={Chinaei, Hamid R. and Chaib-draa, Brahim},
	title={{Learning Dialogue POMDP Models from Data}},
	bookTitle={Advances in Artificial Intelligence: 24th Canadian Conference on Artificial Intelligence},
	series={CAI'11},
	year={2011},
	publisher={Springer Berlin Heidelberg},
	address={Berlin, Heidelberg},
	pages={86--91},
	month={May}
}

@article{cochran2001generic,
	title={{Generic Markov models for Availability Estimation and Failure Characterization in Petroleum Refineries}},
	author={Cochran, Jeffery K. and Murugan, Arvindh and Krishnamurthy, Vijayalakshmi},
	journal={Computers \& Operations Research},
	volume={28},
	number={1},
	pages={1--12},
	year={2001},
	publisher={Elsevier}
}

@misc{cordwellpymdptoolbox,
	title={{Python Markov Decision Process Toolbox}},
	author={Steven A. W. Cordwell},
	url={{https://github.com/sawcordwell/pymdptoolbox}},
	year={2015}
}

@misc{nogueirabayesianoptimization,
	title={{BayesianOptimization: A Python Implementation of Global Optimization with Gaussian Processes}},
	author={Nogueira, Fernando M. F.},
	url={https://github.com/fmfn/BayesianOptimization},
	year={2014},
}

@article{cronvall2009combining,
	title={{Combining Discrete-Time Markov Processes and Probabilistic Fracture Mechanics in RI-ISI Risk Estimates}},
	author={Cronvall, Otso and M{\"a}nnist{\"o}, Ilkka},
	journal={International Journal of Pressure Vessels and Piping},
	volume={86},
	number={11},
	pages={732--737},
	year={2009},
	publisher={Elsevier}
}

@article{dayan1992q,
	title={{Q-Learning}},
	author={Watkins, Christopher J. C. H. and Dayan, Peter},
	journal={Machine learning},
	volume={8},
	number={3-4},
	pages={279--292},
	year={1992},
	publisher={Springer}
}

@article{Degris2010,
	author = {Degris, Thomas and Sigaud, Oliver},
	journal = {{Markov Decision Processes in Artificial Intelligence}},
	pages = {99--126},
	title = {{Factored Markov Decision Processes}},
	year = {2010},
	publisher = {Wiley-IEEE Press}
}

@inproceedings{deisenroth2011pilco,
	title={{PILCO: A Model-Based and Data-Efficient Approach to Policy Search}},
	author={Deisenroth, Marc and Rasmussen, Carl E.},
	booktitle={Proceedings of the 28th International Conference on Machine Learning},
	series={ICML'11},
	pages={465--472},
	year={2011},
	month={January}
}

@article{delgado2011efficient,
	title={{Efficient Solutions to Factored MDPs with Imprecise Transition Probabilities}},
	author={Delgado, Karina Valdivia and Sanner, Scott and De Barros, Leliane Nunes},
	journal={Artificial Intelligence},
	volume={175},
	number={9-10},
	pages={1498--1527},
	year={2011},
	publisher={Elsevier}
}

@article{delgado2016real,
	title={{Real-time dynamic programming for Markov decision processes with imprecise probabilities}},
	author={Delgado, Karina V and de Barros, Leliane N and Dias, Daniel B and Sanner, Scott},
	journal={Artificial Intelligence},
	volume={230},
	pages={192--223},
	year={2016},
	publisher={Elsevier}
}

@article{el2008optimal,
	title={{Optimal Design of a Cogeneration Plant for Power and Desalination Taking Equipment Reliability into Consideration}},
	author={El-Nashar, Ali M.},
	journal={Desalination},
	volume={229},
	number={1},
	pages={21--32},
	year={2008},
	publisher={Elsevier}
}

@inproceedings{epshteyn2008active,
	title={{Active Reinforcement Learning}},
	author={Epshteyn, Arkady and Vogel, Adam and DeJong, Gerald},
	booktitle={Proceedings of the 25th International Conference on Machine Learning},
	series={ICML'08},
	pages={296--303},
	year={2008},
	isbn = {978-1-60558-205-4},
	publisher = {ACM},
	address = {New~York, NY, USA}
}


@article{gales2008application,
	title={{The Application of Hidden Markov Models in Speech Recognition}},
	author={Gales, Mark and Young, Steve},
	journal={Foundations and trends in signal processing},
	volume={1},
	number={3},
	pages={195--304},
	year={2008},
	publisher={Now Publishers Inc.}
}

@article{garcia2015comprehensive,
	title={{A Comprehensive Survey on Safe Reinforcement Learning}},
	author={Garc{\i}a, Javier and Fern{\'a}ndez, Fernando},
	journal={Journal of Machine Learning Research},
	volume={16},
	number={1},
	pages={1437--1480},
	year={2015}
}

@article{Ghahramani2015,
	author = {Ghahramani, Zoubin},
	isbn = {0028-0836},
	issn = {0028-0836},
	journal = {Nature},
	mendeley-groups = {Bayesian Optimization},
	number = {7553},
	pages = {452--459},
	pmid = {26017444},
	title = {{Probabilistic machine learning and artificial intelligence}},
	volume = {521},
	year = {2015}
}

@article{ghavamzadeh2015bayesian,
	title={{Bayesian Reinforcement Learning: A Survey}},
	author={Ghavamzadeh, Mohammad and Mannor, Shie and Pineau, Joelle and Tamar, Aviv and others},
	journal={Foundations and Trends{\textregistered} in Machine Learning},
	volume={8},
	number={5-6},
	pages={359--483},
	year={2015},
	publisher={Now Publishers, Inc.}
}

@article{givan2000bounded,
	title={{Bounded-parameter Markov Decision Processes}},
	author={Givan, Robert and Leach, Sonia and Dean, Thomas},
	journal={Artificial Intelligence},
	volume={122},
	number={1-2},
	pages={71--109},
	year={2000},
	publisher={Elsevier}
}

@article{grimshaw2011markov,
	title={{Markov Chain Models for Delinquency: Transition Matrix Estimation and Forecasting}},
	author={Grimshaw, Scott D. and Alexander, William P.},
	journal={Applied Stochastic Models in Business and Industry},
	volume={27},
	number={3},
	pages={267--279},
	year={2011},
	publisher={Wiley Online Library}
}

@INPROCEEDINGS{gross2008shopbot, 
	author={H. M. Gross and H. J. Boehme and C. Schr{\"o}ter and S. M{\"u}ller and A. K{\"o}nig and C. Martin and M. Merten and A. Bley}, 
	booktitle={2008 IEEE International Conference on Systems, Man and Cybernetics}, 
	title={{ShopBot: Progress in Developing an Interactive Mobile Shopping Assistant for Everyday Use}}, 
	year={2008}, 
	series={SMC'08},
	pages={3471-3478}, 
	keywords={graph theory;intelligent robots;mobile robots;probability;robot vision;service robots;sonar detection;home improvement store;interactive mobile shopping assistant;multimodal user detection;probabilistic approach;robotic shopping assistant;sonar-based gridmap;vision-based graph map;Cognitive robotics;Intelligent robots;Mobile robots;Navigation;Robot sensing systems;Robot vision systems;Sensor phenomena and characterization;Simultaneous localization and mapping;Sonar detection;Testing}, 
	ISSN={1062-922X}, 
	organization={IEEE}
}

@inproceedings{guez2012efficient,
	title={{Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search}},
	author={Guez, Arthur and Silver, David and Dayan, Peter},
	booktitle = {Proceedings of the 25th International Conference on Neural Information Processing Systems},
	series = {NIPS'12},
	pages={1025--1033},
	year={2012},
	publisher = {Curran Associates Inc.},
}

@article{GuillotS17,
	author    = {Matthieu Guillot and Gautier Stauffer},
	title     = {{The Stochastic Shortest Path Problem: {A} polyhedral combinatorics
	perspective}},
	journal   = {CoRR},
	year      = {2017},
}

@article{hawes2016strands,
	title={{The STRANDS Project: Long-Term Autonomy in Everyday Environments}},
	author={Hawes, Nick and Burbridge, Chris and Jovan, Ferdian and Kunze, Lars and Lacerda, Bruno and Mudrov{\'a}, Lenka and Young, Jay and Wyatt, Jeremy and Hebesberger, Denise and K{\"o}rtner, Tobias and others},
	journal={arXiv preprint arXiv:1604.04384},
	year={2016}
}

@ARTICLE{hawes2017strands, 
	author={Hawes, Nick and Burbridge, Chris and Jovan, Ferdian and Kunze, Lars and Lacerda, Bruno and Mudrov{\'a}, Lenka and Young, Jay and Wyatt, Jeremy and Hebesberger, Denise and K{\"o}rtner, Tobias and others}, 
	journal={IEEE Robotics Automation Magazine}, 
	title={{The STRANDS Project: Long-Term Autonomy in Everyday Environments}}, 
	year={2017}, 
	volume={24}, 
	number={3}, 
	pages={146-156}, 
	keywords={Legged locomotion;Monitoring;Navigation;Robustness;Service robots}, 
	ISSN={1070-9932}, 
	month={September},
}

@inproceedings{hester2010generalized,
	title={{Generalized Model Learning for Reinforcement Learning on a Humanoid Robot}},
	author={Hester, Todd and Quinlan, Michael and Stone, Peter},
	booktitle={2010 IEEE International Conference on Robotics and Automation},
	series={ICRA'10},
	pages={2369--2374},
	year={2010},
	pages={2369-2374}, 
	keywords={decision making;decision trees;generalisation (artificial intelligence);humanoid robots;learning (artificial intelligence);mobile robots;multi-robot systems;Aldebaran Nao humanoid robot;autonomous robot;decision making;decision trees;generalized model learning;reinforcement learning;robot programming;Computer science;Decision making;Decision trees;Helicopters;Humanoid robots;Learning systems;Machine learning;Robot programming;Robotics and automation;USA Councils}, 
	ISSN={1050-4729}, 
	month={May},
}

@inproceedings{hester2012rtmba,
	title={{RTMBA: A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control}},
	author={Hester, Todd and Quinlan, Michael and Stone, Peter},
	booktitle={2012 IEEE International Conference on Robotics and Automation},
	series={ICRA'12},
	pages={85--90},
	year={2012},
	keywords={approximation theory;control engineering computing;decision making;learning (artificial intelligence);parallel architectures;real-time systems;robots;RL;RTMBA;autonomous vehicle;decision-making learning;parallel architecture;planning processes;real-time model-based reinforcement learning architecture;robot control;sample based approximate planning methods;Approximation algorithms;Computational modeling;Multicore processing;Planning;Real time systems;Robots}, 
	ISSN={1050-4729}, 
	month={May},
}

@inproceedings{Hoffman2011,
	Author = {Matthew D. Hoffman and Eric Brochu and Nando {de Freitas}},
	Booktitle = {Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence},
	series={UAI'11},
	Title = {{Portfolio Allocation for {B}ayesian Optimization}},
	Year = {2011},
	pages={327--336},
	isbn = {978-0-9749039-7-2},
	publisher = {AUAI Press},
	address = {Arlington, VA, USA}
}

@book{howard1960dynamic,
	author={Howard, Ronald A.},
	year={1960},

    edition = {1st},
    isbn = {0262080095},
    keywords = {1960, dynamic, markov, markov-process, mdp, programming},
    month = {June},
    publisher = {The MIT Press},
    title = {{Dynamic Programming and Markov Processes}},

    }


@article{kaelbling1996reinforcement,
	title={{Reinforcement Learning: A Survey}},
	author={Kaelbling, Leslie Pack and Littman, Michael L. and Moore, Andrew W.},
	journal={Journal of Artificial Intelligence Research},
	volume={4},
	pages={237--285},
	year={1996},
	month={May},
	issn = {1076-9757},
	publisher = {AI Access Foundation}
}

@inproceedings{kawaguchi2015bayesian,
	title={{Bayesian Optimization with Exponential Convergence}},
	author={Kawaguchi, Kenji and Kaelbling, Leslie Pack and Lozano-P{\'e}rez, Tom{\'a}s},
	booktitle={Proceedings of the 28th International Conference on Neural Information Processing Systems},
	series={NIPS'15},
	pages={2809--2817},
	year={2015},
	publisher = {MIT Press},
	address = {Cambridge, MA, USA}
}

@article{kearns2002near,
	title={{Near-Optimal Reinforcement Learning in Polynomial Time}},
	author={Kearns, Michael and Singh, Satinder},
	journal={Machine Learning},
	volume={49},
	number={2-3},
	pages={209--232},
	year={2002},
	publisher={Springer}
}

@inproceedings{koenig1996unsupervised,
	title={{Unsupervised Learning of Probabilistic Models for Robot Navigation}},
	author={Koenig, Sven and Simmons, Reid G.},
	booktitle={Proceedings of the IEEE International Conference on Robotics and Automation},
	series={ICRA'96},
	volume={3},
	pages={2301--2308},
	year={1996},
	ISSN={1050-4729}, 
	month={April},
}

@inproceedings{lacerda2015optimal,
	title={{Optimal Policy Generation for Partially Satisfiable Co-Safe LTL Specifications}},
	author={Lacerda, Bruno and Parker, David and Hawes, Nick},
	booktitle = {Proceedings of the 24th International Conference on Artificial Intelligence},
	series = {IJCAI'15},
	pages={1587--1593},
	year={2015}
}

@article{lee1968maximum,
	title={{Maximum Likelihood and Bayesian Estimation of Transition Probabilities}},
	author={Lee, T. C. and Judge, G. G. and Zellner, Arnold},
	journal={Journal of the American Statistical Association},
	volume={63},
	number={324},
	pages={1162--1179},
	year={1968},
	month={December},
	publisher={Taylor \& Francis Group}
}

@inproceedings{littman1995complexity,
	title={{On the Complexity of Solving Markov Decision Problems}},
	author={Littman, Michael L. and Dean, Thomas L. and Kaelbling, Leslie Pack},
	booktitle={Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence},
	series = {UAI'95},
	isbn = {1-55860-385-9},
	pages={394--402},
	numpages = {9},
	year={1995},
	organization={Morgan Kaufmann Publishers Inc.},
}

@book{lizotte2008practicalx,
	title={Practical bayesian optimization},
	author={Lizotte, Daniel James},
	year={2008},
	publisher={University of Alberta}
}

@phdthesis{lizotte2008practical,
	author       = {Lizotte, Daniel James}, 
	title        = {{Practical Bayesian Optimization}},
	school       = {University of Alberta},
	year         = {2008},
}

@inproceedings{martinez2007active,
	title={{Active Policy Learning for Robot Planning and Exploration under Uncertainty}},
	author={Martinez-Cantin, Ruben and {de Freitas}, Nando and Doucet, Arnaud and Castellanos, Jos{\'e} A},
	booktitle={Robotics: Science and Systems},
	pages={321--328},
	year={2007}
}

@article{MartinezCantin2009,
	author = {Martinez-Cantin, Ruben and {de Freitas}, Nando and Brochu, Eric and Castellanos, Jos{\'{e}} and Doucet, Arnaud},
	eprint = {0712.3744},
	isbn = {0929-5593},
	issn = {09295593},
	journal = {Autonomous Robots},
	keywords = {Active SLAM,Active learning,Active vision,Attention and gaze planning,Bayesian optimization,Dynamic sensor networks,Model predictive control,Online path planning,Policy search,Reinforcement learning,Sequential experimental design},
	number = {2},
	pages = {93--103},
	title = {{A Bayesian Exploration-Exploitation Approach for Optimal Online Sensing and Planning with a Visually Guided Mobile Robot}},
	volume = {27},
	year = {2009}
}

@article{Melo20111757,
	title = "Decentralized \{MDPs\} with sparse interactions ",
	journal = "Artificial Intelligence ",
	volume = "175",
	number = "11",
	pages = "1757 - 1789",
	year = "2011",
	note = "",
	issn = "0004-3702",
	author = "Francisco S. Melo and Manuela Veloso",
	keywords = "Multiagent coordination",
	keywords = "Sparse interaction",
	keywords = "Decentralized Markov decision processes "
}

@misc{Metralabs,  url={http://www.metralabs.com/en/shopping-rfid-robot}, journal={MetraLabs}, publisher={MetraLabs}, author={MetraLabs}, year={2017}}

@article{Minka1999,
	author = {Minka, T.},
	journal = {Technical report, MIT},
	pmid = {1000198457},
	title = {{From Hidden Markov Models to Linear Dynamical Systems}},
	year = {1999}
}

@article{minka2003bayesian,
	title={{Bayesian Inference, Entropy, and the Multinomial Distribution}},
	author={Minka, Tom P.},
	year={2003}
}

@inproceedings{Moldovan2012,
	author = {Moldovan, Teodor Mihai and Abbeel, Pieter},
	isbn = {978-1-4503-1285-1},
	booktitle = {Proceedings of the 29th International Conference on Machine Learning},
	series={ICML'12},
	keywords = {ICML,exploration,machine learning,safe,safety},
	pages = {1451--1458},
	title = {{Safe Exploration in Markov Decision Processes}},
	year = {2012},
	publisher = {Omnipress},
}

@article{morse_simpar_2012,
	author    = {Gilberto Echeverria and
	S\'everin Lemaignan and
	Arnaud Degroote and
	Simon Lacroix and
	Michael Karg and
	Pierrick Koch and
	Charles Lesire and
	Serge Stinckwich},
	title     = {{Simulating Complex Robotic Scenarios with MORSE}},
    journal={Simulation, Modeling, and Programming for Autonomous Robots},
	year      = {2012},
	pages     = {197-208},
	publisher={Springer}
}

@inproceedings{nikovski1999learning,
	title={{Learning Discrete Bayesian Models for Autonomous Agent Navigation}},
	author={Nikovski, Daniel Nikolaev and Nourbakhsh, Illah R.},
	booktitle={Proceedings of the 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation},
	series={CIRA'99},
	pages={137--143},
	year={1999},
}

@inproceedings{nikovski2000learning,
	title={{Learning Probabilistic Models for Decision-Theoretic Navigation of Mobile Robots}},
	author={Nikovski, Daniel Nikolaev and Nourbakhsh, Illah R.},
	booktitle = {Proceedings of the 17th International Conference on Machine Learning},
	series={ICML'00},
	isbn = {1-55860-707-2},
	pages={671--678},
	year={2000},
	publisher = {Morgan Kaufmann Publishers Inc.}
}

@phdthesis{nikovski2002state,
	title={{State-Aggregation Algorithms for Learning Probabilistic Models for Robot Control}},
	isbn = {0-493-53870-4},
	author={Nikovski, Daniel Nikolaev and Nourbakhsh, Illah R.},
	year={2002},
	school={Carnegie Mellon University, The Robotics Institute}
}


@incollection{parent1991stochastic,
	title={{Stochastic Modeling of a Water Resource System: Analytical Techniques versus Synthetic Approaches}},
	author={Parent, E. and Lebdi, F. and Hurand, P.},
	booktitle={{Water Resources Engineering Risk Assessment}},
	pages={415--434},
	year={1991},
	publisher={Springer},
	isbn={978-3-642-76971-9},
}

@article{pasanisi2012estimating,
	title={{Estimating Discrete Markov Models from Various Incomplete Data Schemes}},
	author={Pasanisi, Alberto and Fu, Shuai and Bousquet, Nicolas},
	journal={Computational Statistics \& Data Analysis},
	volume={56},
	number={9},
	pages={2609--2625},
	year={2012},
	month={September},
	publisher={Elsevier},
	issn = {0167-9473},
}

@phdthesis{pazis2012non,
	title={{Non-Parametric Approximate Linear Programming for MDPs}},
	author={Pazis, Jason},
	year={2012},
	school={Duke University}
}

@inproceedings{perchet2014gaussian,
	title={{Gaussian Process Optimization with Mutual Information}},
	author={Contal, Emile and Perchet, Vianney and Vayatis, Nicolas},
	booktitle = {Proceedings of the 31st International Conference on Machine Learning},
	series = {ICML'14},
	volume={32},
	pages={253--261},
	year={2014}
}

@inproceedings{png2011bayesian,
	title={{Bayesian Reinforcement Learning for POMDP-Based Dialogue Systems}},
	author={Png, ShaoWei and Pineau, Joelle},
	booktitle={2011 IEEE International Conference on Acoustics, Speech and Signal Processing},
	series={ICASSP'11},
	pages={2156--2159},
	year={2011},
	month={May},
	ISSN={1520-6149}, 
	organization={IEEE}
}

@book{poole2010artificial,
	title={{Artificial Intelligence: Foundations of Computational Agents}},
	author={Poole, David L. and Mackworth, Alan K.},
	year={2010},
	isbn = {0521519004, 9780521519007},
	publisher={Cambridge University Press}
}

@Inbook{Poupart2010,
	author="Poupart, Pascal",
	editor="Sammut, Claude
	and Webb, Geoffrey I.",
	title="Bayesian Reinforcement Learning",
	bookTitle="Encyclopedia of Machine Learning",
	year="2010",
	publisher="Springer US",
	address="Boston, MA, USA",
	pages="90--93",
	isbn="978-0-387-30164-8",
}

@book{puterman2014markov,
	title={{Markov Decision Processes: Discrete Stochastic Dynamic Programming}},
	author={Puterman, Martin L.},
	year={2014},
	publisher={John Wiley \& Sons}
}

@article{rabiner1989tutorial,
	title={{A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition}},
	author={Rabiner, Lawrence R},
	journal={Proceedings of the IEEE},
	volume={77},
	number={2},
	pages={257--286},
	year={1989},
	publisher={IEEE},
	month={February},
	ISSN={0018-9219}, 
}

@book{rasmussen2006gaussian,
	title={{Gaussian Processes for Machine Learning}},
	author={Rasmussen, Carl Edward and Williams, Christopher K. I.},
	volume={1},
	year={2006},
	publisher={MIT press Cambridge}
}

@article{satia1973markovian,
	title={{Markovian Decision Processes with Uncertain Transition Probabilities}},
	author={Satia, Jay K. and Lave Jr, Roy E.},
	journal={Operations Research},
	volume={21},
	number={3},
	pages={728--740},
	year={1973},
	month={June},
	publisher={INFORMS},
	issn = {0030-364X},
}

@incollection{schaefer2005modeling,
	title={{Modeling Medical Treatment Using Markov Decision Processes}},
	author={Schaefer, Andrew J. and Bailey, Matthew D. and Shechter, Steven M. and Roberts, Mark S.},
	booktitle={{Operations Research and Health Care: A Handbook of Methods and Applications}},
	pages={593--612},
	year={2005},
	publisher={Springer US},
	address={Boston, MA},
	isbn={978-1-4020-8066-1}
}

@article{shahriari2016taking,
	title={{Taking the Human Out of the Loop: A Review of Bayesian Optimization}},
	author={Shahriari, Bobak and Swersky, Kevin and Wang, Ziyu and Adams, Ryan P. and de Freitas, Nando},
	journal={Proceedings of the IEEE},
	volume={104},
	number={1},
	pages={148--175},
	year={2016},
	month={January},
	publisher={IEEE}
}

@techreport{shatkay1997learning,
	title={{Learning Hidden Markov Models with Geometric Information}},
	author={Shatkay, Hagit and Kaelbling, Leslie Pack},
	year={1997},
	publisher = {Brown University}
}

@inproceedings{silver2008sample,
	title={{Sample-based Learning and Search with Permanent and Transient Memories}},
	author={Silver, David and Sutton, Richard S and M{\"u}ller, Martin},
	booktitle={Proceedings of the 25th International Conference on Machine Learning},
	series = {ICML'08},
	isbn = {978-1-60558-205-4},
	pages={968--975},
	year={2008},
	publisher = {ACM},
	address = {New York, NY, USA}
}

@article{singh2000convergence,
	title={{Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms}},
	author={Singh, Satinder and Jaakkola, Tommi and Littman, Michael L and Szepesv{\'a}ri, Csaba},
	journal={Machine learning},
	volume={38},
	number={3},
	pages={287--308},
	year={2000},
	month={March},
	issn = {0885-6125},
	publisher = {Kluwer Academic Publishers},
	address = {Hingham, MA, USA}
}

@inproceedings{snoek2012practical,
	title={{Practical Bayesian Optimization of Machine Learning Algorithms}},
	author={Snoek, Jasper and Larochelle, Hugo and Adams, Ryan P.},
	booktitle={Proceedings of the 25th International Conference on Neural Information Processing Systems},
	series={NIPS'12},
	pages={2951--2959},
	year={2012},
	publisher = {Curran Associates Inc.},
}

@techreport{stolcke1994best,
	title={{Best-First Model Merging for Hidden Markov Model Induction}},
	author={Stolcke, Andreas and Omohundro, Stephen M},
	year={1994},
	publisher={International Computer Science Institute},
	address={Berkeley, CA, USA}
}

@book{sutton1998reinforcement,
	title={{Reinforcement learning: An Introduction}},
	author={Sutton, Richard S. and Barto, Andrew G},
	volume={1},
	number={1},
	year={1998},
	publisher={MIT press Cambridge}
}

@article{teodorescu2009maximum,
	title={{Maximum Likelihood Estimation for Markov Chains}},
	author={Teodorescu, Iuliana},
	year={2009},
	month={May},
	journal={arXiv preprint arXiv:0905.4131},
}

@inproceedings{turchetta2016safe,
	title={{Safe Exploration in Finite Markov Decision Processes with Gaussian Processes}},
	author={Turchetta, Matteo and Berkenkamp, Felix and Krause, Andreas},
	booktitle={Proceedings of the 29th International Conference on Neural Information Processing Systems},
	series={NIPS'16},
	pages={4305--4313},
	year={2016}
}

@inproceedings{wang2016optimization,
	title={{Optimization as Estimation with Gaussian Processes in Bandit Settings}},
	author={Wang, Zi and Zhou, Bolei and Jegelka, Stefanie},
	booktitle={Artificial Intelligence and Statistics},
	series={AISTATS'16},
	year={2016},
    pages={1022--1031},
}

@article{welch2003hidden,
	title={{Hidden Markov Models and the Baum-Welch Algorithm}},
	author={Welch, Lloyd R.},
	journal={IEEE Information Theory Society Newsletter},
	volume={53},
	number={4},
	pages={10--13},
	year={2003}
}

@misc{wiering2004intelligent,
	title={{Intelligent Traffic Light Control}},
	author={Wiering, M. A. and {van} Veenen, J. and Vreeken, Jilles and Koopman, Arne},
	year={2004},
	publisher={Utrecht University: Information and Computing Sciences}
}

@article{wilson2014using,
	title={{Using Trajectory Data to Improve Bayesian Optimization for Reinforcement Learning}},
	author={Wilson, Aaron and Fern, Alan and Tadepalli, Prasad},
	journal={Journal of Machine Learning Research},
	volume={15},
	number={1},
	pages={253--282},
	year={2014}
}

@ARTICLE{young2016, 
	author={S. Young and M. Gašić and B. Thomson and J. D. Williams}, 
	journal={Proceedings of the IEEE}, 
	title={{POMDP-Based Statistical Spoken Dialog Systems: A Review}}, 
	year={2013}, 
	volume={101}, 
	number={5}, 
	pages={1160-1179}, 
	keywords={Bayes methods;Markov processes;optimisation;speech recognition;POMDP-based statistical spoken dialog systems;SDS;data-driven framework;exact model representation;explicit Bayesian model;noisy environments;optimization;partially observable Markov decision processes;reward-driven process;speech recognizers;statistical dialog systems;Belief propagation;Information processing;Learning systems;Markov processes;Mathematical model;Optimization;Speech processing;Speech recognition;Belief monitoring;partially observable Markov decision process (POMDP);policy optimization;reinforcement learning;spoken dialog systems (SDSs)}, 
	ISSN={0018-9219}, 
	month={May},}