Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

December 2006, Vol. 18, No. 12, Pages 2936-2941
(doi: 10.1162/neco.2006.18.12.2936)
© 2006 Massachusetts Institute of Technology
Learning Tetris Using the Noisy Cross-Entropy Method
Article PDF (74.31 KB)
Abstract

The cross-entropy method is an efficient and general optimization algorithm. However, its applicability in reinforcement learning (RL) seems to be limited because it often converges to suboptimal policies. We apply noise for preventing early convergence of the cross-entropy method, using Tetris, a computer game, for demonstration. The resulting policy outperforms previous RL algorithms by almost two orders of magnitude.