13 search results - page 1 / 3 » Variable resolution discretization in the joint space |
ICMLA
2004
13 years 5 months ago
2004
We present JoSTLe, an algorithm that performs value iteration on control problems with continuous actions, allowing this useful reinforcement learning technique to be applied to p...
ICTAI
2003
IEEE
13 years 9 months ago
2003
IEEE
Computing and storing probabilities is a hard problem as soon as one has to deal with complex distributions over multiples random variables. The problem of efficient representati...
ML
2002
ACM
13 years 4 months ago
2002
ACM
Abstract. The problemof state abstractionis of centralimportancein optimalcontrol,reinforcement learning and Markov decision processes. This paper studies the case of variable reso...
ICML
2000
IEEE
14 years 5 months ago
2000
IEEE
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...
UAI
2004
13 years 5 months ago
2004
Mixtures of truncated exponentials (MTE) potentials are an alternative to discretization for representing continuous chance variables in influence diagrams. Also, MTE potentials c...