Is there a difference in the convergence analysis/proof of the chaotic learning automaton compared to the standard LA?


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?

Bagher Zarei

Posted 2020-08-30T20:10:08.450

Reputation: 1

Question was closed 2020-08-31T21:02:01.490

1I don't think you will get any help if you put your article behind a linked paywall. Please put the salient points from your publication in the question here - then we can give feedback here. Use [edit]. If the details are complex and you expect someone to read it and somehow help you, then you will need to provide a non-paywalled version. – Neil Slater – 2020-08-30T20:34:12.480

This question was also asked here:

– nbro – 2020-08-31T09:27:06.287

@nbro That one doesn't even have a link (OP has removed it), so the OP is asking for help with a theory difference between two unreferenced and undescribed approaches, one of which is ostensibly novel. I cannot see how that would get any answer. – Neil Slater – 2020-08-31T18:25:11.247

@NeilSlater I didn't fully read the linked article. If you think I should close this post, let me know and I will close it (right now I cannot dedicate time to read that article). – nbro – 2020-08-31T19:57:01.803

@nbro: Unless you have a subcription to The Journal of Supercomputing then reading the article will cose you ~ £30 (or some equivalent in your area, e.g. $40). So the OP's current link is only useful for users here that already subscribe and are willing to read the article in full. – Neil Slater – 2020-08-31T20:02:58.897

@NeilSlater I am not sure why you say that, maybe I am missing some context, but when I click on that link ( I see the paper (although the pdf does not load, I can see the online version), and I can read it.

– nbro – 2020-08-31T20:11:38.297

@nbor: I only get the abstract, not the full article, and then seem to have choice to log in (I don't have account) or to purchase the full article. Lower down there is also an appendix with tables. But the article itself is not there. – Neil Slater – 2020-08-31T20:52:26.797

@NeilSlater Strange. To me, it says "Access provided by Université de Neuchâtel", so I guess this paper is not accessible to everyone, so I will close it as "needs more details". – nbro – 2020-08-31T21:01:52.880

@BagherZarei Please, try to address Neil's concerns, then I will re-open this post. Not everyone can access your article, but only a few people (only me apparently or people located in certain locations). Also, you're asking about a proof in your own article. I don't understand this. – nbro – 2020-08-31T21:05:04.197

No answers