Can I read Bellman Error Based Feature Generation using Random Projections on Sparse Spaces on EtoBox?

Bellman Error Based Feature Generation using Random Projections on Sparse Spaces by Fard, Mahdi Milani; Grinberg, Yuri; Farahmand, Amir-massoud; Pineau, Joelle; Precup, Doina is a scholarly article available to read on EtoBox.

What is Bellman Error Based Feature Generation using Random Projections on Sparse Spaces about?

We address the problem of automatic generation of features for value function approximation. Bellman Error Basis Functions (BEBFs) have been shown to improve the error of policy evaluation with function approximation, with a convergence rate similar to that of value iteration. We propose a simple, fast and robust algorithm based on random projections to generate BEBFs for sparse feature spaces. We provide a finite sample analysis of the proposed method, and prove that projections logarithmic in the dimension of the original space are enough to guarantee contraction in the error. Empirical results demonstrate the strength of this method.

Author

Fard, Mahdi Milani; Grinberg, Yuri; Farahmand, Amir-massoud; Pineau, Joelle; Precup, Doina

Published

2012

Language

EN