We have recently presented an article entitled Improving learning ability of learning automata using chaos theory.
In this article, a new type of learning automaton called chaotic Learning Automaton (cLA) is presented. In cLA, the chaotic numbers are used instead of the random numbers when choosing the action. Experimental results indicate that the cLA has a higher convergence rate with low convergence time than standard LA. Furthermore, the cLA has more scalability than the standard LA, and its performance will not decrease significantly by increasing the problem size (number of actions).
Is there a difference in the convergence analysis/proof of the cLA compared to the standard LA?