Constrained Cross-Entropy Method for Safe Reinforcement Learning

2020 ◽  
pp. 1-1
Author(s):  
Min Wen ◽  
Ufuk Topcu
Keyword(s):  
Reinforcement Learning ◽  
Entropy Method ◽  
Cross Entropy ◽  
Cross Entropy Method

Learning Tetris Using the Noisy Cross-Entropy Method

2006 ◽  
Vol 18 (12) ◽  
pp. 2936-2941 ◽  
Author(s):  
István Szita ◽  
András Lörincz
Keyword(s):  
Reinforcement Learning ◽  
Optimization Algorithm ◽  
Computer Game ◽  
Entropy Method ◽  
Cross Entropy ◽  
Cross Entropy Method ◽  
The Cross ◽  
Suboptimal Policies

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.

Sign in / Sign up

Export Citation Format

Share Document