Bellman Error Based Feature Generation using Random Projections on Sparse Spaces [article]

Mahdi Milani Fard, Yuri Grinberg, Amir-massoud Farahmand, Joelle Pineau, Doina Precup
2012 arXiv   pre-print
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
more » ... the dimension of the original space are enough to guarantee contraction in the error. Empirical results demonstrate the strength of this method.
arXiv:1207.5554v3 fatcat:gkeuxgs3avgxfbft6tyfjp5jnm