Reinforcement Learning: Publications

Click here to download all publications in a single bibtex file

@inbook{Hoffman:2012,
  title = "Inference Strategies for Solving Semi-{Markov} Decision Processes",
  author = "Matthew Hoffman and Nando de Freitas",
  year = "2012",
  chapter = "5",
  editor = "Enrique Sucar and Eduardo F. Morales and Jesse Hoey",
  pages = "82--96",
  publisher = "Hershey: IGI Global",
  url = "http://mlg.eng.cam.ac.uk/hoffmanm/publications/_download/2010-smdp.pdf",
}

@article{Hoffman:2009b,
  title = "An Expectation Maximization Algorithm for Continuous {Markov} Decision Processes with Arbitrary Reward",
  author = "Matthew Hoffman and Nando de Freitas and Arnaud Doucet and Jan Peters",
  year = "2009",
  journal = "Journal of Machine Learning Research - Proceedings Track for Artificial Intelligence and Statistics (AISTATS)",
  pages = "232--239",
  url = "http://jmlr.org/proceedings/papers/v5/hoffman09a.html",
  volume = "5",
}

@article{Cantin:2009,
  title = "A Bayesian exploration-exploitation approach for optimal online sensing and planning with a visually guided mobile robot",
  author = "Martinez-Cantin, Ruben and Freitas, Nando and Brochu, Eric and Castellanos, José and Doucet, Arnaud",
  year = "2009",
  issn = "0929-5593",
  journal = "Autonomous Robots",
  number = "2",
  pages = "93--103",
  publisher = "Springer US",
  url = "http://dx.doi.org/10.1007/s10514-009-9130-2",
  volume = "27",
  doi = "10.1007/s10514-009-9130-2",
}

@inproceedings{Hoffman:2009,
  title = "New inference strategies for solving {Markov} Decision Processes using reversible jump {MCMC}",
  author = "Matthias Hoffman and Hendrik Kueck and Nando de Freitas and Arnaud Doucet",
  year = "2009",
  address = "Corvallis, Oregon",
  booktitle = "Uncertainty in Artificial Intelligence (UAI)",
  pages = "223--231",
  url = "http://uai.sis.pitt.edu/displayArticleDetails.jsp?mmnu=2&smnu=2&article_id=1658&author_id=4",
}

@incollection{Kueck:2009
year={2009},
  title = "Inference and Learning for Active Sensing, Experimental Design and Control",
  author = "Kueck, Hendrik and Hoffman, Matt and Doucet, Arnaud and Freitas, Nando",
  year = "2009",
  booktitle = "Pattern Recognition and Image Analysis",
  editor = "Araujo, Helder and Mendonca, Ana Maria and Pinho, Armando J. and Torres, Maria Ines",
  isbn = "978-3-642-02171-8",
  pages = "1--10",
  publisher = "Springer Berlin Heidelberg",
  series = "Lecture Notes in Computer Science",
  url = "http://dx.doi.org/10.1007/978-3-642-02172-5_1",
  volume = "5524",
  doi = "10.1007/978-3-642-02172-5_1",
}

@inproceedings{Vogel:2008,
  title = "Target-directed attention: Sequential decision-making for gaze planning",
  author = "Vogel, J. and de Freitas, N.",
  year = "2008",
  booktitle = "IEEE International Conference on Robotics and Automation (ICRA)",
  issn = "1050-4729",
  keywords = "Bayes methods;decision making;planning (artificial intelligence);robot vision;bottom-up attention system;bottom-up saliency information;context information;direct policy search;featural visual saliency;finite-horizon Bayesian sequential decision process;gaze planning;gaze sequence;next best gaze location;object detection precision;probabilistic system;sequential decision making;target-directed attention system;top-down target knowledge;visual search;Bayesian methods;Cameras;Decision making;Detectors;Image analysis;Laboratories;Object detection;Robot vision systems;Robotics and automation;USA Councils",
  pages = "2372--2379",
  doi = "10.1109/ROBOT.2008.4543568",
}

@incollection{Hoffman:2007,
  title = "Bayesian Policy Learning with Trans-Dimensional {MCMC}",
  author = "Matthew Hoffman and Arnaud Doucet and Nando de Freitas and Ajay Jasra",
  year = "2007",
  address = "Cambridge, MA",
  booktitle = "Advances in Neural Information Processing Systems 20",
  editor = "J.C. Platt and D. Koller and Y. Singer and S. Roweis",
  pages = "665--672",
  publisher = "MIT Press",
  url = "http://nips.cc/Conferences/2007/Program/event.php?ID=663",
}

@inproceedings{Menendez:2003,
  title = "Estimation and control of industrial processes with particle filters",
  author = "Morales-Menendez, R. and de Freitas, N. and Poole, D.",
  year = "2003",
  booktitle = "American Control Conference",
  issn = "0743-1619",
  pages = "579--584",
  url = "http://www.cs.ubc.ca/~nando/papers/itesmpaper.pdf",
  volume = "1",
  doi = "10.1109/ACC.2003.1239081",
}