Discussing the article: "Neural networks made easy (Part 52): Research with optimism and distribution correction"
Dmitry hello. Why when training this Expert Advisor Study.mq5, the critics error is not displayed and is -nan(ind). In the log also writes at the end of the study.
Now I tried to delete all your old files from the MQL5/Experts folder and copied them to an empty folder without replacing them. It still does not calculate the error, it says -nan(int).
Hello. I have the same story. Unpacked archive, nan(int). In the common data folder the SoftAC_DICE.set file seems to be empty (16 bytes).
What about the error indicator? Does it really not calculate it, or does it just not output it? Even this is not so important, is the learning process taking place? Not according to the test results.
The arrows are on almost every bar, which should not be the case by the very logic of the market.
Files:
2023-08-06_08-54-44.png
144 kb
I ran the training through the video card and got -nan instead of errors. Tried to run it through the processor and the errors were displayed normally. If someone has figured out how to fix this bug (via video card), please share your thoughts.
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Check out the new article: Neural networks made easy (Part 52): Research with optimism and distribution correction.
As the model is trained based on the experience reproduction buffer, the current Actor policy moves further and further away from the stored examples, which reduces the efficiency of training the model as a whole. In this article, we will look at the algorithm of improving the efficiency of using samples in reinforcement learning algorithms.
As usual, we are much more interested in the efficiency of the model on new data. The generalization ability and performance of the model on unfamiliar data was tested in the strategy tester on historical data for June 2023. As we can see, the testing period immediately follows the training set. This ensures maximum homogeneity of the training and test samples. The test results are presented below.
The presented chart shows a drawdown area in the first ten days of the month. But then it is followed by a period of profitability, which lasts until the end of the month. As a result, the EA received a profit of 7.7% over the course of the month with a maximum drawdown in Equity of 5.46%. In terms of the balance, the drawdown was even smaller and did not exceed 4.87%.
The table of test results shows that during the test the EA performed trades in both directions. A total of 48 positions were opened. 54.17% of them were closed with a profit. The maximum profitable trade is more than 3 times higher than the maximum losing one. The average profitable trade is half as much as the average losing trade. In quantitative terms, on average, for every 3 profitable trades there are 2 unprofitable ones. All this gave a profit factor of 1.74 and a recovery factor of 1.41.
Author: Dmitriy Gizlyk