Proofs of Reinforcement Learning Algorithms

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
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?
http://www.compactech.com/kartoun/videos/Uri_Kartoun_CQ (lamda)_Reinforcment_Learning_August_7_2005.wmv
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
Thanks a lot!
Uri Kartoun.
http://www.compactech.com/kartoun /
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
kartoun wrote:

http://www.compactech.com/kartoun/articles/html/Kartoun_RA_2005_September_3_2005_Accepted.htm
This question would be better directed to comp.ai.
Chris
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
Thanks Chris. I just submitted it to comp.ai. Uri.
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
No, it would not be better directed there. Robots, once given motors and sensors need intelligence.
What would be helpful is an english translation for the mathematically stunted like myself.

http://www.compactech.com/kartoun/articles/html/Kartoun_RA_2005_September_3_2005_Accepted.htm
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
blueeyedpop, I'm going to enhance and explain the algorithm better in future papers (near future). Thanks, -U.
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
This is also related:
Thanks,
Uri.
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
blueeyedpop wrote:

Robots undoubtedly require intelligence. However, in the several years I've followed this forum, I can count the number of substantive AI posts on one hand. That's not to say we aren't interested in AI. This forum just seems more geared towards the mechanics of robotics.
Chris
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
CRM is just that, miscellaneous robotics.
The profusion of mechanical stuff in the group pertains to the availability of outside resources specific to processors and such.
"back in the day", there were a lot of posts, at a lot of different levels.
If Kartoun could digest his data into bits that math morons like myself can grasp, it would be a tremendous contribution to this group.
Mike
It has been the subject of concern as to why it is slow, compared to it's heydey of a decade ago

<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
O.K. I believe that I should post mostly messages related to mechanics. Like that:
http://www.compactech.com/kartoun/videos/Uri_Kartoun_ER1_Self_Docking_November_2004.wmv
Uri.
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
NOOOOOOOOOOOOOOOOO! see the FAQ
http://www.faqs.org/faqs/robotics-faq/part1 /

http://www.compactech.com/kartoun/videos/Uri_Kartoun_ER1_Self_Docking_November_2004.wmv
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
blueeyedpop wrote:

http://www.compactech.com/kartoun/videos/Uri_Kartoun_ER1_Self_Docking_November_2004.wmv
Too long... better to summarize it...
<% if( /^image/.test(type) ){ %>
<% } %>
<%-name%>
CRM is for anything robotic. Please keep posting anything remotely interesting, unless it is spam.

mechanics.
http://www.compactech.com/kartoun/videos/Uri_Kartoun_ER1_Self_Docking_November_2004.wmv