Add a new article
Neural networks made easy (Part 68): Offline Preference-guided Policy Optimization
Neural networks made easy (Part 68): Offline Preference-guided Policy Optimization
Since the first articles devoted to reinforcement learning, we have in one way or another touched upon 2 problems: exploring the environment and determining the reward function. Recent articles have been devoted to the problem of exploration in offline learning. In this article, I would like to introduce you to an algorithm whose authors completely eliminated the reward function.
Developing a Replay System (Part 36): Making Adjustments (II)
Developing a Replay System (Part 36): Making Adjustments (II)
One of the things that can make our lives as programmers difficult is assumptions. In this article, I will show you how dangerous it is to make assumptions: both in MQL5 programming, where you assume that the type will have a certain value, and in MetaTrader 5, where you assume that different servers work the same.
Population optimization algorithms: Micro Artificial immune system (Micro-AIS)
Population optimization algorithms: Micro Artificial immune system (Micro-AIS)
The article considers an optimization method based on the principles of the body's immune system - Micro Artificial Immune System (Micro-AIS) - a modification of AIS. Micro-AIS uses a simpler model of the immune system and simple immune information processing operations. The article also discusses the advantages and disadvantages of Micro-AIS compared to conventional AIS.
Data label for time series mining (Part 6)：Apply and Test in EA Using ONNX
Data label for time series mining (Part 6)：Apply and Test in EA Using ONNX
This series of articles introduces several time series labeling methods, which can create data that meets most artificial intelligence models, and targeted data labeling according to needs can make the trained artificial intelligence model more in line with the expected design, improve the accuracy of our model, and even help the model make a qualitative leap!
Developing a Replay System (Part 34): Order System (III)
Developing a Replay System (Part 34): Order System (III)
In this article, we will complete the first phase of construction. Although this part is fairly quick to complete, I will cover details that were not discussed previously. I will explain some points that many do not understand. Do you know why you have to press the Shift or Ctrl key?
Population optimization algorithms: Evolution Strategies, (μ,λ)-ES and (μ+λ)-ES
Population optimization algorithms: Evolution Strategies, (μ,λ)-ES and (μ+λ)-ES
The article considers a group of optimization algorithms known as Evolution Strategies (ES). They are among the very first population algorithms to use evolutionary principles for finding optimal solutions. We will implement changes to the conventional ES variants and revise the test function and test stand methodology for the algorithms.
Neural networks made easy (Part 66): Exploration problems in offline learning
Neural networks made easy (Part 66): Exploration problems in offline learning
Models are trained offline using data from a prepared training dataset. While providing certain advantages, its negative side is that information about the environment is greatly compressed to the size of the training dataset. Which, in turn, limits the possibilities of exploration. In this article, we will consider a method that enables the filling of a training dataset with the most diverse data possible.
Market math: profit, loss and costs
Market math: profit, loss and costs
In this article, I will show you how to calculate the total profit or loss of any trade, including commission and swap. I will provide the most accurate mathematical model and use it to write the code and compare it with the standard. Besides, I will also try to get on the inside of the main MQL5 function to calculate profit and get to the bottom of all the necessary values from the specification.
Classification models in the Scikit-Learn library and their export to ONNX
Classification models in the Scikit-Learn library and their export to ONNX
In this article, we will explore the application of all classification models available in the Scikit-Learn library to solve the classification task of Fisher's Iris dataset. We will attempt to convert these models into ONNX format and utilize the resulting models in MQL5 programs. Additionally, we will compare the accuracy of the original models with their ONNX versions on the full Iris dataset.
Get 200 usd for your algorithmic trading article!
Get 200 usd for your algorithmic trading article!
Write an article and contribute to the development of algorithmic trading. Share your experience in trading and programming, and we will pay you $200. Additionally, publishing an article on the popular MQL5.com website offers an excellent opportunity to promote your personal brand in a professional community. Thousands of traders will read your work. You can discuss your ideas with like-minded people, gain new experience, and monetize your knowledge.
Population optimization algorithms: Simulated Annealing (SA) algorithm. Part I
Population optimization algorithms: Simulated Annealing (SA) algorithm. Part I
The Simulated Annealing algorithm is a metaheuristic inspired by the metal annealing process. In the article, we will conduct a thorough analysis of the algorithm and debunk a number of common beliefs and myths surrounding this widely known optimization method. The second part of the article will consider the custom Simulated Isotropic Annealing (SIA) algorithm.
Developing an MQTT client for MetaTrader 5: a TDD approach — Final
Developing an MQTT client for MetaTrader 5: a TDD approach — Final
This article is the last part of a series describing our development steps of a native MQL5 client for the MQTT 5.0 protocol. Although the library is not production-ready yet, in this part, we will use our client to update a custom symbol with ticks (or rates) sourced from another broker. Please, see the bottom of this article for more information about the library's current status, what is missing for it to be fully compliant with the MQTT 5.0 protocol, a possible roadmap, and how to follow and contribute to its development.
Developing a Replay System (Part 32): Order System (I)
Developing a Replay System (Part 32): Order System (I)
Of all the things that we have developed so far, this system, as you will probably notice and eventually agree, is the most complex. Now we need to do something very simple: make our system simulate the operation of a trading server. This need to accurately implement the way the trading server operates seems like a no-brainer. At least in words. But we need to do this so that the everything is seamless and transparent for the user of the replay/simulation system.
Developing a Replay System (Part 31): Expert Advisor project — C_Mouse class (V)
Developing a Replay System (Part 31): Expert Advisor project — C_Mouse class (V)
We need a timer that can show how much time is left till the end of the replay/simulation run. This may seem at first glance to be a simple and quick solution. Many simply try to adapt and use the same system that the trading server uses. But there's one thing that many people don't consider when thinking about this solution: with replay, and even m ore with simulation, the clock works differently. All this complicates the creation of such a system.
Developing a Replay System — Market simulation (Part 24): FOREX (V)
Developing a Replay System — Market simulation (Part 24): FOREX (V)
Today we will remove a limitation that has been preventing simulations based on the Last price and will introduce a new entry point specifically for this type of simulation. The entire operating mechanism will be based on the principles of the forex market. The main difference in this procedure is the separation of Bid and Last simulations. However, it is important to note that the methodology used to randomize the time and adjust it to be compatible with the C_Replay class remains identical in both simulations. This is good because changes in one mode lead to automatic improvements in the other, especially when it comes to handling time between ticks.
Creating a trading robot for Moscow Exchange. Where to start?
Creating a trading robot for Moscow Exchange. Where to start?
Many traders on Moscow Exchange would like to automate their trading algorithms, but they do not know where to start. The MQL5 language offers a huge range of trading functions, and it additionally provides ready classes that help users to make their first steps in algo trading.
Design Patterns in software development and MQL5 (Part 2): Structural Patterns
Design Patterns in software development and MQL5 (Part 2): Structural Patterns
In this article, we will continue our articles about Design Patterns after learning how much this topic is more important for us as developers to develop extendable, reliable applications not only by the MQL5 programming language but others as well. We will learn about another type of Design Patterns which is the structural one to learn how to design systems by using what we have as classes to form larger structures.
Population optimization algorithms: Spiral Dynamics Optimization (SDO) algorithm
Population optimization algorithms: Spiral Dynamics Optimization (SDO) algorithm
The article presents an optimization algorithm based on the patterns of constructing spiral trajectories in nature, such as mollusk shells - the spiral dynamics optimization (SDO) algorithm. I have thoroughly revised and modified the algorithm proposed by the authors. The article will consider the necessity of these changes.
Design Patterns in software development and MQL5 (Part I): Creational Patterns
Design Patterns in software development and MQL5 (Part I): Creational Patterns
There are methods that can be used to solve many problems that can be repeated. Once understand how to use these methods it can be very helpful to create your software effectively and apply the concept of DRY ((Do not Repeat Yourself). In this context, the topic of Design Patterns will serve very well because they are patterns that provide solutions to well-described and repeated problems.
Neural networks made easy (Part 63): Unsupervised Pretraining for Decision Transformer (PDT)
Neural networks made easy (Part 63): Unsupervised Pretraining for Decision Transformer (PDT)
We continue to discuss the family of Decision Transformer methods. From previous article, we have already noticed that training the transformer underlying the architecture of these methods is a rather complex task and requires a large labeled dataset for training. In this article we will look at an algorithm for using unlabeled trajectories for preliminary model training.