Test Bib « Beyond Today

Test Bib

2011

G. C. S. J. S. L. M. L. V. M. P. Q. B. U. E. Z. Jordan Ash Monica Babes, “Scratchable Devices: User-Friendly Programming for Household Appliances,” in Human Computer Interaction International (HCII-11), 2011.
[Bibtex]

@inproceedings{ash11,
  title = {Scratchable Devices: User-Friendly Programming for Household Appliances},
  author = {Jordan Ash, Monica Babes, Gal Cohen, Sameen Jalal, Sam Lichtenberg, Michael Littman, Vukosi Marivate, Phillip Quiza, Blase Ur, Emily Zhang},
  year = {2011},
  booktitle = {Human Computer Interaction International (HCII-11)}
}

M. Babes, V. Marivate, M. Littman, and K. Subramanian, “Apprenticeship Learning About Multiple Intentions,” in Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011.
[Bibtex]

@InProceedings{Babes11,
  author =    {Monica Babes and Vukosi Marivate and Michael Littman and Kaushik Subramanian},
  title =     {Apprenticeship Learning About Multiple Intentions},
  booktitle = {Proceedings of the 28th International Conference on Machine Learning (ICML-11)},
  year =      {2011},
  url  =      {http://www.icml-2011.org/papers/478_icmlpaper.pdf}
}

M. Wunder, M. Kaisers, J. R. Yaros, and M. Littman, “Using iterated reasoning to predict opponent strategies,” in The 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-11), 2011.
[Bibtex]

@inproceedings{Wunder11,
 author = {Michael Wunder and Michael Kaisers and John Robert Yaros and Michael L. Littman},
 title = {Using iterated reasoning to predict opponent strategies},
 booktitle = {The 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-11)},
 year = {2011},
 url = {http://dl.acm.org/citation.cfm?id=2031678.2031702},
}

S. Goschin, M. Littman, and D. Ackley, “The Effects of Selection on Noisy Fitness Optimization,” in Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (GECCO-11), 2011.
[Bibtex]

@inproceedings{Goschin11,
  author = {Sergiu Goschin and Michael L. Littman and David H. Ackley},
  title = {The Effects of Selection on Noisy Fitness Optimization},
  booktitle = {Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (GECCO-11)},
  year = {2011},
  url = {http://doi.acm.org/10.1145/2001576.2001853}
}

C. Mansley, A. Weinstein, and M. Littman, “Sample-Based Planning for Continuous Action Markov Decision Processes,” in International Conference on Planning and Scheduling (ICAPS-11), 2011.
[Bibtex]

@inproceedings{mansley11,
  author    = {Christopher R. Mansley and
               Ari Weinstein and
               Michael L. Littman},
  title     = {Sample-Based Planning for Continuous Action Markov Decision Processes},
  booktitle = {International Conference on Planning and Scheduling (ICAPS-11)},
  year      = {2011},
  url       = {http://aaai.org/ocs/index.php/ICAPS/ICAPS11/paper/view/2679},
}

J. Asmuth and M. Littman, “Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search,” in Proceedings of The 27th Conference on Uncertainty in Artificial Intelligence (UAI-11), 2011.
[Bibtex]

@inproceedings{asmuth11,
  title = "Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search",
  author = "John Asmuth and Michael Littman",
  year = "2011",
  booktitle = "Proceedings of The 27th Conference on Uncertainty in Artificial Intelligence (UAI-11)",
  url = "http://paul.rutgers.edu/~jasmuth/bayes/asmuth11.pdf"
}

2010

M. Wunder, M. Littman, and M. Babes, “Classes of Multiagent Q-learning Dynamics with epsilon-greedy Exploration,” , 2010.
[Bibtex]

@inproccedings{wunder10,
  author = {Michael Wunder and Michael Littman and Monica Babes},
  title = {Classes of Multiagent Q-learning Dynamics with epsilon-greedy Exploration},
  booktitle = {The 27th International Conference on Machine Learning (ICML-10)},
  year = {2010},
  url = {http://www.icml2010.org/papers/191.pdf}
}

T. Walsh, S. Goschin, and M. Littman, “Integrating Sample-based Planning and Model-based Reinforcement Learning,” in Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI-10), 2010.
[Bibtex]

@inproceedings{walsh10b,
       title = "Integrating Sample-based Planning and Model-based Reinforcement Learning",
       author = "Thomas J. Walsh and Sergiu Goschin and Michael Littman",
       year = "2010",
       booktitle = "Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI-10)",
       url = "http://paul.rutgers.edu/~sgoschin/papers/aaai10.pdf"
}

A. Nouri and M. Littman, “Dimension Reduction and Its Application to Exploration in Continuous Spaces,” in Machine Learning Journal, 2010, pp. 85-98.
[Bibtex]

@inproceedings{nouri10,
       title = "Dimension Reduction and Its Application to Exploration in Continuous Spaces",
       author = "Ali Nouri and Michael L. Littman",
       year = "2010",
       booktitle = "Machine Learning Journal",
       volume = "81",
       number = "1",
       pages = "85--98",
       DOI = "10.1007/s10994-010-5202-y",
       url = "http://www.springerlink.com/content/hlt3146235268271/"
}

T. Walsh, K. Subramanian, M. Littman, and C. Diuk, “Generalizing Apprenticeship Learning across Hypothesis Classes,” in Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010.
[Bibtex]

@inproceedings{walsh10,
       title = "Generalizing Apprenticeship Learning across Hypothesis Classes",
       author = "Thomas J. Walsh and Kaushik Subramanian and Michael Littman and Carlos Diuk",
       year = "2010",
       booktitle = "Proceedings of the 27th International Conference on Machine Learning (ICML-10)",
       url = "http://paul.rutgers.edu/~cdiuk/papers/icml10Traces.pdf"
}

2009

T. Walsh, I. Szita, C. Diuk, and M. Littman, “Exploring Compact Reinforcement-Learning Representations with Linear Regression,” in Proceedings of The 25th Conference on Uncertainty in Artificial Intelligence (UAI-09), 2009.
[Bibtex]

@inproceedings{walsh09,
       title = "Exploring Compact Reinforcement-Learning Representations with Linear Regression",
       author = "Thomas J. Walsh and Istv\'an Szita and Carlos Diuk and Michael L. Littman",
       year = "2009",
       booktitle = "Proceedings of The 25th Conference on Uncertainty in Artificial Intelligence (UAI-09)",
       url = "http://paul.rutgers.edu/~thomaswa/pub/uai09Linear.pdf"
}

J. Asmuth, L. Li, M. Littman, A. Nouri, and D. Wingate, “A Bayesian Sampling Approach to Exploration in Reinforcement Learning,” in Proceedings of The 25th Conference on Uncertainty in Artificial Intelligence (UAI-09), 2009.
[Bibtex]

@inproceedings{asmuth09,
       title = "A Bayesian Sampling Approach to Exploration in Reinforcement Learning",
       author = "John Asmuth and Lihong Li and Michael L. Littman and Ali Nouri and David Wingate",
       year = "2009",
       booktitle = "Proceedings of The 25th Conference on Uncertainty in Artificial Intelligence (UAI-09)",
       url = "http://paul.rutgers.edu/~jasmuth/pub/uai09-boss.pdf"
}

L. L. Carlos Diuk and B. Leffler, “The Adaptive k-Meteorologists Problem and Its Application to Structure Learning and
Feature Selection in Reinforcement Learning,” in Proceedings of the Twenty-Sixth International Conference on Machine Learning
(ICML-09), 2009.
[Bibtex]

@inproceedings{diuk09,
       title = "The Adaptive k-Meteorologists Problem and Its Application to Structure Learning and
Feature Selection in Reinforcement Learning",
       author = "Carlos Diuk, Lihong Li and Bethany R. Leffler",
       year = "2009",
       booktitle = "Proceedings of the Twenty-Sixth International Conference on Machine Learning
(ICML-09)",
       url = "http://paul.rutgers.edu/~cdiuk/papers/meteorologist.pdf"
}

T. Walsh, A. Nouri, L. Li, and M. Littman, “Planning and Learning in Environments with Delayed Feedback,” Journal of Autonomous Agents and Multi-Agent Systems, vol. 18, iss. 1, pp. 83-105, 2009.
[Bibtex]

@article{walsh09,
    author = {Thomas J. Walsh and Ali Nouri and Lihong Li and Michael L. Littman},
    title = {Planning and Learning in Environments with Delayed Feedback},
    journal = {Journal of Autonomous Agents and Multi-Agent Systems},
    year = {2009},
    volume = {18},
    number = {1},
    pages = {83--105},
    url = {http://dx.doi.org/10.1007/s10458-008-9056-7}
}

A. Nouri and M. Littman, “Multi-resolution Exploration in Continuous Spaces,” in Proceedings of Neural Information Processing Systems, 2009.
[Bibtex]

@inproceedings{nouri08,
    author = "Ali Nouri and Michael L. Littman",
    title = "Multi-resolution Exploration in Continuous Spaces",
    booktitle = "Proceedings of Neural Information Processing Systems",
    url = "http://www.cs.rutgers.edu/~nouri/pubs/nips08-MRE.pdf",
    year = "2009",
    type = "bib2html"
}

L. Li, M. Littman, and C. Mansley, “Online Exploration in Least-Squares Policy Iteration,” in Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-09), 2009.
[Bibtex]

@inproceedings{li09,
    author = "Lihong Li and Michael L. Littman and Christopher R. Mansley",
    title = "Online Exploration in Least-Squares Policy Iteration",
    booktitle = "Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-09)",
    url = "http://www.cs.rutgers.edu/~lihong/pub/Li09Online.pdf",
    year = "2009",
    type = "bib2html"
}

A. Strehl, L. Li, and M. Littman, “Reinforcement learning in general MDPs: PAC analysis,” Journal of Machine Learning Research, vol. 10, pp. 2413-2444, 2009.
[Bibtex]

@article{strehl09,
    author = "Alexander L. Strehl and Lihong Li and Michael L. Littman",
    title = "Reinforcement learning in general {MDPs}: {PAC} analysis",
    journal = "Journal of Machine Learning Research",
    year = "2009",
    volume = "10",
    pages = "2413--2444",
    url = "http://jmlr.csail.mit.edu/papers/v10/strehl09a.html"
}

E. Brunskill, B. Leffler, L. Li, M. Littman, and N. Roy, “Provably efficient learning with typed parametric models,” Journal of Machine Learning Research, vol. 10, pp. 1955–1988,, 2009.
[Bibtex]

@article{brunskill09,
    author = "Emma Brunskill and Bethany R. Leffler and Lihong Li and Michael L. Littman and Nichlos Roy",
    title = "Provably efficient learning with typed parametric models",
    journal = "Journal of Machine Learning Research",
    year = "2009",
    volume = "10",
    pages = "1955--1988,",
    url = "http://jmlr.csail.mit.edu/papers/v10/brunskill09a.html"
}

2008

B. Leffler, C. Mansley, and M. Littman, “Efficient Learning of Dynamics Models using Terrain Classification,” in Proceedings of the International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems, 2008.
[Bibtex]

@inproceedings{leffler08,
  author = "Bethany R. Leffler and Christopher R. Mansley and Michael L. Littman",
  title = "Efficient Learning of Dynamics Models using Terrain Classification",
  booktitle = "Proceedings of the International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems",
  year = "2008",
  location = "Patras, Greece",
  url = "http://www.cs.rutgers.edu/~bleffler/publications/erlars08.pdf"
}

T. Walsh and M. Littman, ” Efficient Learning of Action Schemas and Web-Service Descriptions,” in Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI-08), 2008.
[Bibtex]

@inproceedings{walsh08,
       title = " Efficient Learning of Action Schemas and Web-Service Descriptions",
       author = "Thomas J. Walsh and Michael L. Littman",
       year = "2008",
       booktitle = "Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI-08)",
       url = "http://paul.rutgers.edu/~thomaswa/pub/aaai08.pdf"
}

J. Asmuth, M. Littman, and R. Zinkov, “Potential-based Shaping in Model-based Reinforcement Learning,” in Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI-08), 2008.
[Bibtex]

@inproceedings{asmuth08,
       title = "Potential-based Shaping in Model-based Reinforcement Learning",
       author = "John Asmuth and Michael L. Littman and Robert Zinkov",
       year = "2008",
       booktitle = "Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI-08)",
       url = "http://paul.rutgers.edu/~jasmuth/pub/aaai08-shaping.pdf"
}

F. Yaman, T. Walsh, M. Littman, and M. desJardins, “Democratic Approximation of Lexicographic Preference Models,” in Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08), 2008.
[Bibtex]

@inproceedings{yaman08,
       title = "Democratic Approximation of Lexicographic Preference Models",
       author = "Fusun Yaman and Thomas J. Walsh and Michael L. Littman and Marie desJardins",
       year = "2008",
       booktitle = "Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08)",
       url = "http://paul.rutgers.edu/~thomaswa/pub/icml08Pref.pdf"
}

C. Diuk, A. Cohen, and M. Littman, “An Object-Oriented Representation for Efficient Reinforcement Learning,” in Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08), 2008.
[Bibtex]

@inproceedings{diuk08,
       title = "An Object-Oriented Representation for Efficient Reinforcement Learning",
       author = "Carlos Diuk and Andre Cohen and Michael Littman",
       year = "2008",
       booktitle = "Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08)",
       url = "http://paul.rutgers.edu/~cdiuk/papers/OORL.pdf"
}

L. Li and M. Littman, “Efficient Value-Function Approximation via Online
Linear Regression,” in International Symposium on Artificial
Intelligence and Mathematics, 2008.
[Bibtex]

@inproceedings{li08,
    author = "Lihong Li and Michael Littman",
    title = "Efficient Value-Function Approximation via Online
                  Linear Regression",
    booktitle = "International Symposium on Artificial
                  Intelligence and Mathematics",
    year = "2008",
    url = "http://www.research.rutgers.edu/~lihong/pub/Li08Efficient.pdf"
}

M. Babes, E. M. de Cote, and M. Littman, “Social Reward Shaping in the Prisoner’s Dilemma,” in Autonomous Agents and Multiagent Systems 2008, 2008.
[Bibtex]

@inproceedings{babes08,
    title = "Social Reward Shaping in the Prisoner's Dilemma",
    author = "Monica Babes and Enrique Munoz de Cote and Michael Littman",
    booktitle = "Autonomous Agents and Multiagent Systems 2008",
    year = "2008",
    url = "http://portal.acm.org/citation.cfm?id=1402880"
}

A. Strehl and M. Littman, “Online Linear Regression and Its Application to
Model-Based Reinforcement Learning,” in Proceedings of Neural Information Processing Systems, 2008.
[Bibtex]

@inproceedings{strehl08,
    author = "Alexander L. Strehl and Michael L. Littman",
    title = "Online Linear Regression and Its Application to
                  Model-Based Reinforcement Learning",
    booktitle = "Proceedings of Neural Information Processing Systems",
    year = "2008"
}

L. Li, “A Worst-Case Comparison between Temporal Difference and Residual Gradient with Linear Function Approximation,” in Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08), 2008.
[Bibtex]

@inproceedings{li08a,
    title = "A Worst-Case Comparison between Temporal Difference and Residual Gradient with Linear Function Approximation",
    author = "Lihong Li",
    year = "2008",
    booktitle = "Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08)",
    url = "http://www.cs.rutgers.edu/~lihong/pub/Li08Worst.pdf",
    type = "bib2html"
}

L. Li, M. Littman, and T. Walsh, “Knows What It Knows: A Framework for Self-Aware Learning,” in Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08), 2008.
[Bibtex]

@inproceedings{li08b,
    title = "Knows What It Knows: A Framework for Self-Aware Learning",
    author = "Lihong Li and Michael L. Littman and Thomas J. Walsh",
    year = "2008",
    booktitle = "Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08)",
    url = "http://www.cs.rutgers.edu/~lihong/pub/Li08Knows.pdf",
    type = "bib2html"
}

R. Parr, L. Li, G. Taylor, C. Painter-Wakefield, and M. Littman, “An Analysis of Linear Models, Linear Value-Function Approximation, and Feature Selection for Reinforcement Learning,” in Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08), 2008.
[Bibtex]

@inproceedings{parr08,
    title = "An Analysis of Linear Models, Linear Value-Function Approximation, and Feature Selection for Reinforcement Learning",
    author = "Ronald Parr and Lihong Li and Gavin Taylor and Christopher Painter-Wakefield and Michael L. Littman",
    year = "2008",
    booktitle = "Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML-08)",
    url = "http://www.cs.rutgers.edu/~lihong/pub/Parr08Analysis.pdf",
    type = "bib2html"
}

L. L. M. L. Emma Brunskill Bethany R. Leffler and N. Roy, “CORL: A Continuous-State Offset-Dynamics Reinforcement Learner,” in Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI-08), 2008.
[Bibtex]

@inproceedings{brunskill08,
    title = "{CORL}: A Continuous-State Offset-Dynamics Reinforcement Learner",
    author = "Emma Brunskill, Bethany R. Leffler, Lihong Li, Michael L. Littman, and Nicholas Roy",
    year = "2008",
    booktitle = "Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI-08)",
    url = "http://www.cs.rutgers.edu/~lihong/pub/Brunskill08Corl.pdf",
    type = "bib2html"
}

2007

B. Leffler, M. Littman, and T. Edmunds, “Efficient Reinforcement Learning with Relocatable
Action Models,” in Proceedings of the Twenty-Second Conference on
Artificial Intelligence (AAAI-07), 2007.
[Bibtex]

@inproceedings{leffler07,
    booktitle = "Proceedings of the Twenty-Second Conference on
                  Artificial Intelligence (AAAI-07)",
    year = "2007",
    title = "Efficient Reinforcement Learning with Relocatable
                  Action Models",
    author = "Bethany R. Leffler and Michael L. Littman and
                  Timothy Edmunds",
    url = "http://www.research.rutgers.edu/~tedmunds/publications/RAM-aaai2007.pdf"
}

T. Walsh, A. Nouri, L. Li, and M. Littman, “Planning and Learning in Environments with Delayed
Feedback,” in Proceedings of the 18th European Conference on
Machine Learning (ECML-07), 2007.
[Bibtex]

@inproceedings{walsh07b,
    author = "Thomas J. Walsh and Ali Nouri and Lihong Li and
                  Michael L. Littman",
    title = "Planning and Learning in Environments with Delayed
                  Feedback",
    booktitle = "Proceedings of the 18th European Conference on
                  Machine Learning (ECML-07)",
    year = "2007",
    url = "http://paul.rutgers.edu/~thomaswa/ecml07Delayed.pdf"
}

A. Strehl, C. Diuk, and M. Littman, “Efficient Structure Learning in Factored-state MDPs,” in Proceedings of the Twenty-Second National
Conference on Artificial Intelligence (AAAI-07), 2007.
[Bibtex]

@inproceedings{strehl07,
    author = "Alexander L. Strehl and Carlos Diuk and Michael L. Littman",
    year = "2007",
    title = "Efficient Structure Learning in Factored-state {MDP}s",
    booktitle = "Proceedings of the Twenty-Second National
                  Conference on Artificial Intelligence (AAAI-07)",
    was = "diuk07",
    url = "http://paul.rutgers.edu/~cdiuk/papers/StructLearnAAAI07.pdf"
}

R. Parr, C. Painter-Wakefield, L. Li, and M. Littman, “Analyzing Feature Generation for Value-Function
Approximation,” in International Conference on Machine Learning
(ICML-2007), 2007.
[Bibtex]

@inproceedings{parr07,
    title = "Analyzing Feature Generation for Value-Function
                  Approximation",
    author = "Ronald Parr and Christopher Painter-Wakefield and
                  Lihong Li and Michael Littman",
    booktitle = "International Conference on Machine Learning
                  (ICML-2007)",
    year = "2007",
    url = "http://www.research.rutgers.edu/~lihong/pub/Parr07Analyzing.pdf"
}

T. Walsh and M. Littman, “Planning with Conceptual Models Mined from User
Behavior,” in Proceedings of the AAAI-07 Workshop on Acquiring
Planning Knowledge via Demonstration, 2007.
[Bibtex]

@inproceedings{walsh07,
    author = "Thomas J. Walsh and Michael L. Littman",
    title = "Planning with Conceptual Models Mined from User
                  Behavior",
    year = "2007",
    booktitle = "Proceedings of the AAAI-07 Workshop on Acquiring
                  Planning Knowledge via Demonstration",
    url = "http://paul.rutgers.edu/~thomaswa/aaai07Wkshp1.pdf"
}

F. Zeng and M. Littman, “Just-in-time Failure Detection,” in ICAC-2007 Workshop on Adaptive Methods in
Autonomic Computing Systems (AMACS), 2007.
[Bibtex]

@inproceedings{zeng07,
    title = "Just-in-time Failure Detection",
    author = "Fancong Zeng and Michael L. Littman",
    booktitle = "ICAC-2007 Workshop on Adaptive Methods in
                  Autonomic Computing Systems (AMACS)",
    year = "2007"
}

A. Greenwald and M. Littman, “Introduction to the special issue on learning and
computational game theory,” Machine Learning, vol. 67, iss. 1–2, 2007.
[Bibtex]

@article{greenwald07,
    title = "Introduction to the special issue on learning and
                  computational game theory",
    author = "Amy Greenwald and Michael L. Littman",
    volume = "67",
    number = "1--2",
    year = "2007",
    journal = "Machine Learning"
}

M. Zinkevich, A. Greenwald, and M. Littman, “A hierarchy of prescriptive goals for multiagent
learning,” Artificial Intelligence, vol. 171, pp. 440-447, 2007.
[Bibtex]

@article{zinkevich07,
    title = "A hierarchy of prescriptive goals for multiagent
                  learning",
    author = "Martin Zinkevich and Amy Greenwald and Michael
                  L. Littman",
    journal = "Artificial Intelligence",
    year = "2007",
    volume = "171",
    pages = "440--447"
}

T. Walsh and M. Littman, “A Multiple Representation Approach To Learning
Dynamical Systems,” in Computational Approaches to Representation Change
During Learning and Development: AAAI Fall
Symposium, 2007.
[Bibtex]

@inproceedings{walsh07c,
    author = "Thomas J. Walsh and Michael L. Littman",
    title = "A Multiple Representation Approach To Learning
                  Dynamical Systems",
    booktitle = "Computational Approaches to Representation Change
                  During Learning and Development: AAAI Fall
                  Symposium",
    year = "2007",
    url = "http://www.research.rutgers.edu/~thomaswa/FS04WalshT.pdf"
}

2006

M. Littman, N. Ravi, A. Talwar, and M. Zinkevich, “An Efficient Optimal-Equilibrium Algorithm for
Two-Player Game Trees,” in Twenty-Second Conference on Uncertainty in
Artificial Intelligence (UAI-06), 2006.
[Bibtex]

@inproceedings{littman06,
    author = "Michael L. Littman and Nishkam Ravi and Arjun Talwar
                  and Martin Zinkevich",
    title = "An Efficient Optimal-Equilibrium Algorithm for
                  Two-Player Game Trees",
    booktitle = "Twenty-Second Conference on Uncertainty in
                  Artificial Intelligence (UAI-06)",
    url = "http://www.cs.ualberta.ca/~maz/publications/bestnash.pdf",
    year = "2006"
}

D. Roberts, M. Nelson, C. L. Isbell Jr., M. Mateas, and M. Littman, “Targeting Specific Distributions of Trajectories in
MDPs,” in Proceedings of The Twenty-First National
Conference on Artificial Intelligence, 2006.
[Bibtex]

@inproceedings{roberts06,
    author = "David L. Roberts and Mark J. Nelson and
                  Isbell, Jr., Charles Lee and Michael Mateas and Michael
                  L. Littman",
    title = "Targeting Specific Distributions of Trajectories in
                  {MDP}s",
    booktitle = "Proceedings of The Twenty-First National
                  Conference on Artificial Intelligence",
    url = "http://www-static.cc.gatech.edu/~robertsd/papers/aaai06-ttdmdp.pdf",
    year = "2006"
}

A. Strehl, L. Li, and M. Littman, “Incremental Model-based Learners With Formal
Learning-Time Guarantees,” in Proceedings of the 22nd Conference on Uncertainty
in Artificial Intelligence (UAI 2006), 2006.
[Bibtex]

@inproceedings{strehl06c,
    author = "Alexander L. Strehl and Lihong Li and Michael
                  L. Littman",
    title = "Incremental Model-based Learners With Formal
                  Learning-Time Guarantees",
    booktitle = "Proceedings of the 22nd Conference on Uncertainty
                  in Artificial Intelligence (UAI 2006)",
    year = "2006",
    url = "http://www.cs.rutgers.edu/~strehl/papers/UAI06IncrementalModelBasedRL.pdf"
}

A. Strehl, L. Li, E. Wiewiora, J. Langford, and M. Littman, “PAC Model-free Reinforcement Learning,” in Proceedings of the Twenty-third International
Conference on Machine Learning (ICML-06), 2006.
[Bibtex]

@inproceedings{strehl06,
    title = "{PAC} Model-free Reinforcement Learning",
    author = "Alexander L. Strehl and Lihong Li and Eric Wiewiora
                  and John Langford and Michael L. Littman",
    year = "2006",
    booktitle = "Proceedings of the Twenty-third International
                  Conference on Machine Learning (ICML-06)",
    url = "http://www.cs.rutgers.edu/~strehl/papers/ICML06PACModelFreeRL.pdf",
    type = "bib2html"
}

L. Li, T. Walsh, and M. Littman, “Towards a Unified Theory of State Abstraction for
MDPs,” in Ninth International Symposium on Artificial
Intelligence and Mathematics, 2006.
[Bibtex]

@inproceedings{li06,
    booktitle = "Ninth International Symposium on Artificial
                  Intelligence and Mathematics",
    title = "Towards a Unified Theory of State Abstraction for
                  {MDP}s",
    author = "Lihong Li and Thomas J. Walsh and Michael
                  L. Littman",
    year = "2006",
    type = "bib2html",
    url = "http://anytime.cs.umass.edu/aimath06/proceedings/P21.pdf"
}

C. Diuk, M. Littman, and A. Strehl, “A Hierarchical Approach to Efficient Reinforcement
Learning in Deterministic Domains,” in Fifth International Conference on Autonomous
Agents and Multiagent Systems (AAMAS-06), 2006.
[Bibtex]

@inproceedings{diuk06,
    title = "A Hierarchical Approach to Efficient Reinforcement
                  Learning in Deterministic Domains",
    author = "Carlos Diuk and Michael Littman and Alexander
                  Strehl",
    booktitle = "Fifth International Conference on Autonomous
                  Agents and Multiagent Systems (AAMAS-06)",
    year = "2006",
    type = "bib2html",
    url = "http://paul.rutgers.edu/~cdiuk/papers/HRL_AAMAS.pdf"
}

A. Strehl, L. Li, and M. Littman, “PAC Reinforcement Learning Bounds for RTDP and
Rand-RTDP,” in AAAI 2006 Workshop on Learning For Search, 2006.
[Bibtex]

@inproceedings{strehl06d,
    author = "Alexander L. Strehl and Lihong Li and Michael
                  L. Littman",
    title = "{PAC} Reinforcement Learning Bounds for {RTDP} and
                  Rand-{RTDP}",
    booktitle = "AAAI 2006 Workshop on Learning For Search",
    url = "http://www.cs.rutgers.edu/~strehl/papers/AAAI06WkspPACRTDP.pdf",
    year = "2006"
}

A. Strehl, C. Mesterharm, M. Littman, and H. Hirsh, “Experience-Efficient Learning in Associative Bandit
Problems,” in Proceedings of the Twenty-third International
Conference on Machine Learning (ICML-06), 2006.
[Bibtex]

@inproceedings{strehl06b,
    title = "Experience-Efficient Learning in Associative Bandit
                  Problems",
    author = "Alexander L. Strehl and Chris Mesterharm and Michael
                  L. Littman and Haym Hirsh",
    year = "2006",
    booktitle = "Proceedings of the Twenty-third International
                  Conference on Machine Learning (ICML-06)",
    url = "http://www.cs.rutgers.edu/~strehl/papers/ICML06AssociativeBandit.pdf",
    type = "bib2html"
}

2005

H. Younes, M. Littman, D. Weissman, and J. Asmuth, “The First Probabilistic Track of the International Planning Competition,” in Journal of Artificial Intelligence Research 24, Pages 851-887, 2005.
[Bibtex]

@inproceedings{younes05,
       title = "The First Probabilistic Track of the International Planning Competition",
       author = "Hakan L. S. Younes and Michael L. Littman and David Weissman and John Asmuth",
       year = "2005",
       booktitle = "Journal of Artificial Intelligence Research 24, Pages 851-887",
       url = "http://public.jair.fetch.com/media/1880/live-1880-2554-jair.pdf"
}

M. Zinkevich, A. Greenwald, and M. Littman, “Cyclic Equilibria in Markov Games,” in Advances in Neural Information Processing Systems
18, 2005.
[Bibtex]

@inproceedings{zinkevich05,
    author = "Martin Zinkevich and Amy R. Greenwald and Michael
                  L. Littman",
    title = "Cyclic Equilibria in {M}arkov Games",
    booktitle = "Advances in Neural Information Processing Systems
                  18",
    url = "http://www.cs.brown.edu/people/amy/papers/nips.pdf",
    year = "2005"
}

N. Ravi, N. Dandekar, P. Mysore, and M. Littman, “Activity Recognition from Accelerometer Data,” in Seventeenth Innovative Applications of Artificial
Intelligence Conference, 2005, pp. 1541-1546.
[Bibtex]

@inproceedings{ravi05,
    author = "Nishkam Ravi and Nikhil Dandekar and Preetham Mysore
                  and Michael L. Littman",
    title = "Activity Recognition from Accelerometer Data",
    year = "2005",
    pages = "1541--1546",
    booktitle = "Seventeenth Innovative Applications of Artificial
                  Intelligence Conference",
    type = "bib2html",
    url = "http://paul.rutgers.edu/~nikhild/Accpaper.pdf"
}

A. Strehl and M. Littman, “A Theoretical Analysis of Model-Based Interval
Estimation,” in Proceedings of the Twenty-second International
Conference on Machine Learning (ICML-05), 2005, pp. 857-864.
[Bibtex]

@inproceedings{strehl05b,
    title = "A Theoretical Analysis of Model-Based Interval
                  Estimation",
    author = "Alexander L. Strehl and Michael L. Littman",
    year = "2005",
    pages = "857--864",
    booktitle = "Proceedings of the Twenty-second International
                  Conference on Machine Learning (ICML-05)",
    url = "http://paul.rutgers.edu/~strehl/papers/icml05-mbie.pdf",
    type = "bib2html"
}

L. Li and M. Littman, “Lazy Approximation for Solving Continuous
Finite-Horizon MDPs,” in The Twentieth National Conference on Artificial
Intelligence, 2005, pp. 1175-1180.
[Bibtex]

@inproceedings{li05,
    author = "Lihong Li and Michael L. Littman",
    title = "Lazy Approximation for Solving Continuous
                  Finite-Horizon {MDP}s",
    booktitle = "The Twentieth National Conference on Artificial
                  Intelligence",
    year = "2005",
    pages = "1175--1180",
    type = "bib2html",
    url = "http://www.research.rutgers.edu/~lihong/pub/Li05Lazy.pdf"
}

B. Leffler, M. Littman, A. Strehl, and T. Walsh, “Efficient Exploration With Latent Structure,” in Proceedings of Robotics: Science and Systems, 2005.
[Bibtex]

@inproceedings{leffler05,
    title = "Efficient Exploration With Latent Structure",
    author = "Bethany R. Leffler and Michael L. Littman and Alexander
                  L. Strehl and Thomas J. Walsh",
    year = "2005",
    url = "http://www.cs.rutgers.edu/~strehl/papers/RSS05LatentStructure.pdf",
    booktitle = "Proceedings of Robotics: Science and Systems"
}

2004

A. Strehl and M. Littman, “An Empirical Evaluation of Interval Estimation for
Markov Decision Processes,” in The 16th IEEE International Conference on Tools with
Artificial Intelligence (ICTAI-2004), 2004, pp. 128-135.
[Bibtex]

@inproceedings{strehl04,
    year = "2004",
    title = "An Empirical Evaluation of Interval Estimation for
                  {M}arkov Decision Processes",
    booktitle = "The 16th IEEE International Conference on Tools with
                  Artificial Intelligence (ICTAI-2004)",
    pages = "128--135",
    author = "Alexander L. Strehl and Michael L. Littman",
    noturl = "http://paul.rutgers.edu/~strehl/papers/EmpiricalMBIE.pdf",
    url = "http://www.cs.rutgers.edu/~mlittman/papers/ictai04-mbie.pdf",
    type = "bib2html"
}

D. LeRoux and M. Littman, Reinforcement Learning using LCS in Continuous
State Space, 2004.
[Bibtex]

@unpublished{leroux04,
    year = "2004",
    title = "Reinforcement Learning using {LCS} in Continuous
                  State Space",
    author = "David LeRoux and Michael Littman",
    note = "International Workshop on Learning Classifier Systems, Extended Abstract",
    url = "http://www.cs.rutgers.edu/~mlittman/papers/iwlcs04-rect.pdf",
    type = "bib2html"
}

M. Littman, N. Ravi, E. Fenson, and R. Howard, “Reinforcement Learning for Autonomic Network Repair,” in 1st International Conference on Autonomic
Computing (ICAC 2004), 2004, pp. 284-285.
[Bibtex]

@inproceedings{littman04b,
    year = "2004",
    title = "Reinforcement Learning for Autonomic Network Repair",
    author = "Michael L. Littman and Nishkam Ravi and Eitan Fenson
                  and Rich Howard",
    booktitle = "1st International Conference on Autonomic
                  Computing (ICAC 2004)",
    pages = "284--285",
    url = "http://www.cs.rutgers.edu/~mlittman/papers/icac04-csfr.pdf",
    type = "bib2html"
}

2003

M. Littman, T. Nguyen, H. Hirsh, E. Fenson, and R. Howard, “Cost-Sensitive Fault Remediation for Autonomic
Computing,” in Workshop on AI and Autonomic Computing:
Developing a Research Agenda for Self-Managing
Computer Systems, 2003.
[Bibtex]

@inproceedings{littman03e,
    title = "Cost-Sensitive Fault Remediation for Autonomic
                  Computing",
    author = "Michael L. Littman and Thu Nguyen and Haym Hirsh and
                  Eitan M. Fenson and Richard Howard",
    year = "2003",
    booktitle = "Workshop on AI and Autonomic Computing:
                  {D}eveloping a Research Agenda for Self-Managing
                  Computer Systems",
    url = "http://www.cs.rutgers.edu/~mlittman/papers/ijcai03-csfr.pdf",
    type = "bib2html"
}

Comments are closed.

Subscribe via RSS

Beyond Today

Tomorrow has never been brighter….

Test Bib

2011

2010

2009

2008

2007

2006

2005

2004

2003

Home

Recent Posts

Recent Comments

InstaGallery

Archives

Social Media

AI and ML

Friends

Listen

Music

My Sites

News

Services

Technology

Visited

Twitter Updates

LInks Shared

Recent Posts

Categories

Pages