IJCAI
2003
14 years 5 months ago
2003
We present an approximate policy iteration algorithm that uses rollouts to estimate the value of each action under a given policy in a subset of states and a classifier to general...
CDC
2008
IEEE
14 years 10 months ago
2008
IEEE
— This paper presents a new approximate policy iteration algorithm based on support vector regression (SVR). It provides an overview of commonly used cost approximation architect...
Publication
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...
ICML
2003
IEEE
15 years 5 months ago
2003
IEEE
