Graphics enhanced version of this site

Publications, Remi Munos

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Influence and Variance of a Markov Chain: Application to Adaptive Discretization in Optimal Control
  R. Munos and A. Moore
  IEEE Conference on Decision and Control, Vol. 2, December, 1999, pp. 1464 - 1469. [Abstract]
  Download: pdf [207 KB], ps.gz [180 KB] copyrighted

• Variable resolution discretization for high-accuracy solutions of optimal control problems
  R. Munos and A. Moore
  International Joint Conference on Artificial Intelligence, August, 1999. [Abstract]
  Download: pdf [430 KB], ps.gz [315 KB] copyrighted

• Cached Sufficient Statistics for Automated Mining and Discovery from Massive Data Sources
  A. Moore, J. Schneider, B. Anderson, S. Davies, P. Komarek, M.S. Lee, M. Meila, R. Munos, K. Myers, and D. Pelleg
  July, 1999.
  Download: pdf [191 KB], ps.gz [113 KB] copyrighted

• Gradient Descent Approaches to Neural-Net-Based Solutions of the Hamilton-Jacobi-Bellman Equation
  R. Munos, L. Baird, and A. Moore
  International Joint Conference on Neural Networks, July, 1999. [Abstract]
  Download: pdf [192 KB], ps.gz [128 KB] copyrighted

• A Study of Reinforcement Learning in the Continuous Case by the Means of Viscosity Solutions
  R. Munos
  Machine Learning Journal, 1999. [Abstract]
  Download: pdf [359 KB], ps.gz [171 KB] copyrighted

• Variable Resolution Discretization in Optimal Control
  R. Munos and A. Moore
  Machine Learning Journal, 1999.
  Download: pdf [534 KB], ps.gz [343 KB] copyrighted

• Barycentric Interpolator for Continuous Space and Time Reinforcement Learning
  R. Munos and A. Moore
  Neural Information Processing Systems, MIT Press, Vol. 11, December, 1998. [Abstract]
  Download: pdf [170 KB], ps.gz [48 KB] copyrighted

• A general convergence method for Reinforcement Learning in the continuous case
  R. Munos
  European Conference on Machine Learning, 1998. [Abstract]
  Download: pdf [579 KB], ps.gz [237 KB] copyrighted

• A convergent Reinforcement Learning algorithm in the continuous case based on a Finite Difference method
  R. Munos
  1997 International Joint Conference on Artificial Intelligence (IJCAI '97), 1997. [Abstract]
  Download: pdf [658 KB], ps.gz [232 KB] copyrighted

• Finite-Element methods with local triangulation refinement for continuous Reinforcement Learning problems
  R. Munos
  European Conference on Machine Learning 1997, 1997. [Abstract]
  Download: pdf [569 KB], ps.gz [293 KB] copyrighted

• Reinforcement Learning for Continuous Stochastic Control Problems
  R. Munos and P. Bourgine
  Neural Information Processing Systems, 1997. [Abstract]
  Download: pdf [454 KB], ps.gz [164 KB] copyrighted

• A Convergent Reinforcement Learning algorithm in the continuous case: the Finite-Element Reinforcement Learning
  R. Munos
  International Conference on Machine Learning 1996 (ICML '96), 1996. [Abstract]
  Download: pdf [201 KB], ps.gz [67 KB] copyrighted

• Using Finite-Differences methods for approximating the value function of continuous Reinforcement Learning problems
  R. Munos
  International Symposium on Multi-Technology Information Processing 1996, 1996. [Abstract]
  Download: pdf [315 KB], ps.gz [119 KB] copyrighted