Discussion of article "Neural networks made easy (Part 35): Intrinsic Curiosity Module" - page 2

Dmitriy Gizlyk 2023.06.22 13:56 #11

francobritannique #:
Can I second the request for more details on how exactly the model should be created? I would really like to experiment with this EA but this is blocking me!

Hi, You can use model from next article.

Neural networks made easy (Part 36): Relational Reinforcement Learning

www.mql5.com

In the reinforcement learning models we discussed in previous article, we used various variants of convolutional networks that are able to identify various objects in the original data. The main advantage of convolutional networks is the ability to identify objects regardless of their location. At the same time, convolutional networks do not always perform well when there are various deformations of objects and noise. These are the issues which the relational model can solve.

Dmitriy Gizlyk 2023.06.22 14:09 #12

yuk ping wong #:

Do you have the model file? it seems not in the zip file.

Do you have more information about how to create the model by the NetCreator as well or at least share this file? the EA can't start run withtout those file.

as said below:

To train the EA, all models were created using the NetCreator tool. It should be added that to enable EA operation in the strategy tester, the model files must be located in the terminal common directory 'Terminal\Common\Files', since each agent operates in its own sandbox, so they can exchange data only via the common terminals folder.

Hi, about creating model with NetCreator you can read at "Neural networks made easy (Part 31): Evolutionary algorithms"

Neural networks made easy (Part 31): Evolutionary algorithms

www.mql5.com

In the previous article, we started exploring non-gradient optimization methods. We got acquainted with the genetic algorithm. Today, we will continue this topic and will consider another class of evolutionary algorithms.

1 2

New comment