Sciweavers

Share
IJCAI
2003
9 years 11 months ago
Approximate Policy Iteration using Large-Margin Classifiers
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...
Michail G. Lagoudakis, Ronald Parr
CDC
2008
IEEE
206views Control Systems» more  CDC 2008»
10 years 5 months ago
Approximate dynamic programming using support vector regression
— 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...
Brett Bethke, Jonathan P. How, Asuman E. Ozdaglar

Publication
334views
10 years 7 months ago
Rollout Sampling Approximate Policy Iteration
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...
Christos Dimitrakakis, Michail G. Lagoudakis
books