NASA Logo, National Aeronautics and Space Administration

Bio


Research Interests

I am interested in many aspects of AI, problem solving and decision-making. My past research focuses on decision-theoretic planning and machine learning. My current work aims at scaling up decision-theoretic approaches to planning problems encountered in space exploration and aeronautics.

Here is a list of topics of interest:

  • Planning under uncertainty, Markov Decision Processes (MDPs), Partially Observable MDPs (POMDPs);

  • Machine Learning, Reinforcement Learning, Ant Colony Optimization;

  • Planetary exploration.

I am currently the principal investigator of the project Decision Theoretic Planning for Planetary Exploration founded by NASA Intelligent Systems program.

Select Publications

The artificial evolution of cooperation
Nicolas Meuleau and Claude Lattaud
In Artificial Evolution, Proceedings of AE 95, Lecture Notes on Computer Science, Springer-Verlag, p.159-180, 1996.

Hierarchical solution of Markov decision processes using macro-actions
Milos Hauskrecht, Nicolas Meuleau, Craig Boutilier, Leslie Pack Kaelbling and Thomas L. Dean
In Proceedings of the Fourteenth Conference on Uncertainty In Artificial Intelligence (UAI-98), Morgan Kaufmann, San Francisco, p. 220-229, 1998.

Solving very large weakly coupled Markov decision processes
Nicolas Meuleau, Milos Hauskrecht, Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Thomas L. Dean and Craig Boutilier
In Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), MIT Press, Cambridge, p. 165-172, 1998.

Learning policies with external memory
Leonid Peshkin, Nicolas Meuleau and Leslie Pack Kaelbling
In Proceedings of the Sixteenth International Conference on Machine Learning (ICML-99), Morgan Kaufmann, San Francisco, CA, 307-314, 1999.

Exploration of multi-state environments: Local measure and back-propagation of uncertainty
Nicolas Meuleau and Paul Bourgine
Machine Learning, vol. 35(2), p. 117-154, 1999.

Solving POMDPs by searching the space of finite policies
Nicolas Meuleau, Kee-Eung Kim, Leslie Pack Kaelbling and Anthony R. Cassandra
In Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI-99), Morgan Kaufmann, San Francisco, CA, p. 417-426, 1999.

Learning finite-state controllers for partially observable environments
Nicolas Meuleau, Leonid Peshkin, Kee-Eung Kim and Leslie Pack Kaelbling
In Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI-99), Morgan Kaufmann, San Francisco, CA, p. 427-436, 1999.

Approximate solutions to factored Markov decision processes via greedy search in the space of finite controllers
Kee-Eung Kim, Thomas L. Dean and Nicolas Meuleau
In Proceedings of the Fifth International Conference on Artificial Intelligence Planning and Scheduling (ICAPS-2000), AAAI Press, Menlo Park, CA, p. 323-330, 2000.

Learning to cooperate via policy search
Leonid Peshkin, Kee-Eung Kim, Nicolas Meuleau and Leslie Pack Kaelbling
In Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI-2000), Morgan Kaufmann, San Francisco, CA, p. 489-496, 2000.

Exploration in Gradient-Based Reinforcement Learning
Nicolas Meuleau, Leonid Peshkin and Kee-Eung Kim
MIT AI Memo 2001-003 (Technical Report 1713), 2001.

A model of partially observable state game and its optimality
Matteo Golfarelli and Nicolas Meuleau
Applied Intelligence, vol. 14(3), p. 273-281, 2001.

Ant colony optimization and stochastic gradient descent
Nicolas Meuleau and Marco Dorigo
Artificial Life, vol. 8(2), p. 103-121, 2002.

Planning under continuous time and uncertainty: A challenge for AI
John Bresina, Richard Dearden, Nicolas Meuleau, Sailesh Ramakrishnan, David Smith and Rich Washington
In Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI-02), Morgan Kaufmann, San Francisco, CA, p. 77–84, 2002.

Incremental contingency planning
Richard Dearden, Nicolas Meuleau, Sailesh Ramakrishman, David Smith and Rich Washington
In ICAPS-03: Proceedings of the Workshop on Planning under Uncertainty and Incomplete Information, Trento, Italy, p. 38–47, 2003.

Optimal limited contingency planning
Nicolas Meuleau and David E. Smith
In Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI-03), Morgan Kaufmann, San Francisco, CA, p. 417-426, 2003.

Scaling up decision theoretic planning to planetary rover problems
Nicolas Meuleau, Richard Dearden and Rich Washington
In AAAI-04: Proceedings of the Workshop on Learning and Planning in Markov Processes: Advances and Challenges, Technical Report WS-04-08, AAAI Press, Menlo Park, CA, p. 66-71, 2004.

Dynamic programming for structured continuous Markov decision problems
Zhengzhu Feng, Richard Dearden, Nicolas Meuleau and Rich Washington
In Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI-04), AUAI Press, Menlo Park, CA, p. 154-161, 2004.

Model-based search for combinatorial optimization: A critical survey
Mark Zlochin, Mauro Birattari, Nicolas Meuleau and Marco Dorigo
Annals of Operations Research, vol. 131, p. 373-395, 2004.

Planning with continuous resources in stochastic domains
Mausam, Emmanuel Benazera, Ronen Brafman, Nicolas Meuleau and Eric Hansen
In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI-05), Professional Book Center, Denver, CO, p. 1244-1251, 2005.

Stochastic over-subscription planning using hierarchies of MDPs
Nicolas Meuleau, Ronen Brafman and Emmanuel Benazera
In Proceedings of the Sixteenth International Conference on Automated Planning and Scheduling (ICAPS-06), AAAI Press, Menlo Park, CA, p. 121-130, 2006.

Hierarchical heuristic forward search in stochastic domains
Nicolas Meuleau and Ronen Brafman
In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI-07), AAAI Press, Menlo Park, CA, p. 2542-2549, 2007.

Contact

Computer Scientist, QSS Group.

Ames Research Center
Mail Stop M.S. 269-3
Moffett Field, CA 94035

Phone: 604-2138
Fax: 650 604 7563

First Gov logo
NASA Logo - nasa.gov