Proofs of Reinforcement Learning Algorithms

[kartoun]

Hi,

 

I'm suggesting a new reinforcement learning algorithm applied in my case on robots, please see:

http://www.compactech.com/kartoun/articles/html/Kartoun_RA_2005_September_3_2005_Accepted.htm'>http://www.compactech.com/kartoun/articles/html/Kartoun_RA_2005_September_3_2005_Accepted.htm

 

I would like to describe the algorithm more scientifically; define it mathematically much better than described in the

 

paper.

 

I'm asking for guidance of how to prove an algorithm, for example in the form of convergence or superiority. How can I

 

demonstrate advantages or disadvantages of an algorithm mathematically? How can I prove convergence or divergence? How can

 

I show if it is better or worse than other algorithms?

 

I intend applying it for the task of finding optimal grasping, lifting and shaking policies of suspicious bags (contain

 

anthrax, Ebola microbes or SARS), please see an initial experiment:

 

http://www.compactech.com/kartoun/videos/Uri_Kartoun_Plastic_Bag_Experiment_January_2_2006.wmv'>http://www.compactech.com/kartoun/videos/Uri_Kartoun_Plastic_Bag_Experiment_January_2_2006.wmv

 

Thanks a lot!

 

Uri Kartoun.

 

http://www.compactech.com/kartoun/