Proofs of Reinforcement Learning Algorithms

Posted by kartoun on January 4, 2006, 9:56 pm

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?

I've already tested the algorithm on a mobile robot for navigation,
please see:

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/

Posted by Chris Spencer on January 5, 2006, 10:20 pm

kartoun wrote:

> 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

This question would be better directed to comp.ai.

Chris

Posted by kartoun on January 6, 2006, 1:19 pm

Thanks Chris. I just submitted it to comp.ai.
Uri.

Posted by blueeyedpop on January 7, 2006, 10:50 am

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.

> kartoun wrote:

> > 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

> This question would be better directed to comp.ai.
> Chris

Posted by kartoun on January 15, 2006, 1:14 pm

blueeyedpop, I'm going to enhance and explain the algorithm better in
future papers (near future).
Thanks,
-U.

Page 1 of 3 1 2 3 > last >>

Subject
Posted In
Date

Human-Robot Collaboration and Reinforcement Learning
General Robotics Forum
2006-05-30

Robot Planning algorithms - free on-line book
General Robotics Forum
2008-11-12

What is anger, emotion, state, behavior?
General Robotics Forum
2006-10-01

CFP: Special Session on Autonomous Agent Learning
Industrial Control Group
2008-01-09

MindForth Programming Journal (MFPJ) 2010 August 30
General Robotics Forum
2010-10-26