11 search results - page 1 / 3 » Model-Free Least-Squares Policy Iteration |
NIPS
2001
13 years 5 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
ECAI
2006
Springer
13 years 8 months ago
2006
Springer
Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
AAAI
2006
13 years 6 months ago
2006
We present a new algorithm, called incremental least squares policy iteration (ILSPI), for finding the infinite-horizon stationary policy for partially observable Markov decision ...
ICML
2010
IEEE
13 years 5 months ago
2010
IEEE
PKDD
2009
Springer
13 years 11 months ago
2009
Springer
The goal of approximate policy evaluation is to “best” represent a target value function according to a specific criterion. Temporal difference methods and Bellman residual m...