Can I read Gradient-based Reinforcement Planning in Policy-Search Methods on EtoBox?

Gradient-based Reinforcement Planning in Policy-Search Methods by Kwee, Ivo; Hutter, Marcus; Schmidhuber, Juergen is a scholarly article available to read on EtoBox.

What is Gradient-based Reinforcement Planning in Policy-Search Methods about?

We introduce a learning method called ``gradient-based reinforcement planning'' (GREP). Unlike traditional DP methods that improve their policy backwards in time, GREP is a gradient-based method that plans ahead and improves its policy before it actually acts in the environment. We derive formulas for the exact policy gradient that maximizes the expected future reward and confirm our ideas with numerical experiments.

Author

Kwee, Ivo; Hutter, Marcus; Schmidhuber, Juergen

Published

2001

Language

EN