Add a new article
Neural networks are easy (Part 59): Dichotomy of Control (DoC)
Neural networks are easy (Part 59): Dichotomy of Control (DoC)
In the previous article, we got acquainted with the Decision Transformer. But the complex stochastic environment of the foreign exchange market did not allow us to fully implement the potential of the presented method. In this article, I will introduce an algorithm that is aimed at improving the performance of algorithms in stochastic environments.
ALGLIB numerical analysis library in MQL5
ALGLIB numerical analysis library in MQL5
The article takes a quick look at the ALGLIB 3.19 numerical analysis library, its applications and new algorithms that can improve the efficiency of financial data analysis.
Neural networks made easy (Part 56): Using nuclear norm to drive research
Neural networks made easy (Part 56): Using nuclear norm to drive research
The study of the environment in reinforcement learning is a pressing problem. We have already looked at some approaches previously. In this article, we will have a look at yet another method based on maximizing the nuclear norm. It allows agents to identify environmental states with a high degree of novelty and diversity.
Brute force approach to patterns search (Part VI): Cyclic optimization
Brute force approach to patterns search (Part VI): Cyclic optimization
In this article I will show the first part of the improvements that allowed me not only to close the entire automation chain for MetaTrader 4 and 5 trading, but also to do something much more interesting. From now on, this solution allows me to fully automate both creating EAs and optimization, as well as to minimize labor costs for finding effective trading configurations.
Modified Grid-Hedge EA in MQL5 (Part I): Making a Simple Hedge EA
Modified Grid-Hedge EA in MQL5 (Part I): Making a Simple Hedge EA
We will be creating a simple hedge EA as a base for our more advanced Grid-Hedge EA, which will be a mixture of classic grid and classic hedge strategies. By the end of this article, you will know how to create a simple hedge strategy, and you will also get to know what people say about whether this strategy is truly 100% profitable.
Neural networks made easy (Part 53): Reward decomposition
Neural networks made easy (Part 53): Reward decomposition
We have already talked more than once about the importance of correctly selecting the reward function, which we use to stimulate the desired behavior of the Agent by adding rewards or penalties for individual actions. But the question remains open about the decryption of our signals by the Agent. In this article, we will talk about reward decomposition in terms of transmitting individual signals to the trained Agent.
Developing a quality factor for Expert Advisors
Developing a quality factor for Expert Advisors
In this article, we will see how to develop a quality score that your Expert Advisor can display in the strategy tester. We will look at two well-known calculation methods – Van Tharp and Sunny Harris.
Neural networks made easy (Part 51): Behavior-Guided Actor-Critic (BAC)
Neural networks made easy (Part 51): Behavior-Guided Actor-Critic (BAC)
The last two articles considered the Soft Actor-Critic algorithm, which incorporates entropy regularization into the reward function. This approach balances environmental exploration and model exploitation, but it is only applicable to stochastic models. The current article proposes an alternative approach that is applicable to both stochastic and deterministic models.
Neural networks made easy (Part 49): Soft Actor-Critic
Neural networks made easy (Part 49): Soft Actor-Critic
We continue our discussion of reinforcement learning algorithms for solving continuous action space problems. In this article, I will present the Soft Actor-Critic (SAC) algorithm. The main advantage of SAC is the ability to find optimal policies that not only maximize the expected reward, but also have maximum entropy (diversity) of actions.
Neural networks made easy (Part 45): Training state exploration skills
Neural networks made easy (Part 45): Training state exploration skills
Training useful skills without an explicit reward function is one of the main challenges in hierarchical reinforcement learning. Previously, we already got acquainted with two algorithms for solving this problem. But the question of the completeness of environmental research remains open. This article demonstrates a different approach to skill training, the use of which directly depends on the current state of the system.
Neural networks made easy (Part 44): Learning skills with dynamics in mind
Neural networks made easy (Part 44): Learning skills with dynamics in mind
In the previous article, we introduced the DIAYN method, which offers the algorithm for learning a variety of skills. The acquired skills can be used for various tasks. But such skills can be quite unpredictable, which can make them difficult to use. In this article, we will look at an algorithm for learning predictable skills.
Neural networks made easy (Part 41): Hierarchical models
Neural networks made easy (Part 41): Hierarchical models
The article describes hierarchical training models that offer an effective approach to solving complex machine learning problems. Hierarchical models consist of several levels, each of which is responsible for different aspects of the task.
Alternative risk return metrics in MQL5
Alternative risk return metrics in MQL5
In this article we present the implementation of several risk return metrics billed as alternatives to the Sharpe ratio and examine hypothetical equity curves to analyze their characteristics.
How to create a simple Multi-Currency Expert Advisor using MQL5 (Part 2): Indicator Signals: Multi Timeframe Parabolic SAR Indicator
How to create a simple Multi-Currency Expert Advisor using MQL5 (Part 2): Indicator Signals: Multi Timeframe Parabolic SAR Indicator
The Multi-Currency Expert Advisor in this article is Expert Advisor or trading robot that can trade (open orders, close orders and manage orders for example: Trailing Stop Loss and Trailing Profit) for more than 1 symbol pair only from one symbol chart. This time we will use only 1 indicator, namely Parabolic SAR or iSAR in multi-timeframes starting from PERIOD_M15 to PERIOD_D1.
Another MQL5 OOP Class
Another MQL5 OOP Class
This article shows you how to build an Object-Oriented Expert Advisor from scratch, from conceiving a theoretical trading idea to programming a MQL5 EA that makes that idea real in the empirical world. Learning by doing is IMHO a solid approach to succeed, so I am showing a practical example in order for you to see how you can order your ideas to finally code your Forex robots. My goal is also to invite you to adhere the OO principles.