51 search results - page 2 / 11 » Improving Approximate Value Iteration Using Memories and Pre... |
Publication
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
ICAI
2009
13 years 2 months ago
2009
- We address the issues of improving the feature generation methods for the value-function approximation and the state space approximation. We focus the improvement of feature gene...
SIGMETRICS
2000
ACM
13 years 9 months ago
2000
ACM
We present a new approximation algorithm based on an exact representation of the state space S, using decision diagrams, and of the transition rate matrix R, using Kronecker algeb...
PKDD
2009
Springer
13 years 11 months ago
2009
Springer
Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
Publication
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...