52 search results - page 1 / 11 » Error Bounds for Approximate Policy Iteration |
ICML
2003
IEEE
14 years 5 months ago
2003
IEEE
ML
2008
ACM
13 years 4 months ago
2008
ACM
Abstract. We consider batch reinforcement learning problems in continuous space, expected total discounted-reward Markovian Decision Problems. As opposed to previous theoretical wo...
Publication
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
NIPS
2003
13 years 5 months ago
2003
We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic fini...
ICIP
1999
IEEE
14 years 6 months ago
1999
IEEE
This paper presents an iterative algorithm for approximating gray-scale images with adaptive triangular meshes ensuring a given tolerance. At each iteration, the algorithm applies...