All about MQL5 Wizard : create robots without programming. - page 7

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 41): Deep-Q-Networks

Deep-Q-Networks (DQN) are another reinforcement learning algorithm, besides Q-Learning that we looked at in this article, but they, unlike Q-Learning, use neural networks to forecast the q-value and the next action to be taken by the agent. It is similar/ related to Q-Learning in that a Q-Table is still involved, where the cumulative knowledge on actions and states from previous ‘episodes’ gets stored. In fact, it shares the same Wikipedia page as Q-Learning as can be seen from the links where it's defined essentially as a variant of Q-Learning.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 42): ADX Oscillator

The ADX indicator is an oscillator that is meant to measure how strong a given trend in the market is for the security to which it is attached. This article thus, like some that were preceding it, examines the various patterns exhibited by this indicator in a custom signal class file, for wizard assembled Expert Advisors. We review one pattern at a time as we have in the previous articles covering RSI, Bollinger Bands, and the RSI and then conclude with a test that includes all patterns to get a sense of which has the highest weighting.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 43): Reinforcement Learning with SARSA

Reinforcement Learning (RL) allows trading systems to learn from their environment or market data and thus improve their ability to trade over time. RL enables adaptation to changing market conditions, making it suitable for certain dynamic financial markets and securities. Financial markets are unpredictable, as often they feature a high degree of uncertainty. RL excels at making decisions under uncertainty by continuously adjusting its actions based on received feedback (rewards), thus being very helpful to traders when handling volatile market conditions.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 44): Average True Range (ATR) technical indicator

The Average True Range is a common and popular volatility indicator, which arguably, for forex traders, is the ‘closest-thing’ to volume data. Developed as an indicator which was meant to track price bar range without skimping on intra-bar price changes, it has become a bit of a stalwart in the industry not just for filtering entry signals but also in guiding on position sizing. We look at this indicator by decomposing it into possible patterns as we have been doing with the previous indicator’s articles with perhaps the main difference being we look into patterns outside of the custom signal class by also considering the custom money management class for wizard assembled Expert Advisors.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 45): Reinforcement Learning with Monte-Carlo

This article continues our look at reinforcement learning by considering another algorithm, namely the Monte-Carlo. This algorithm is very similar and in fact arguably encompasses both Q-Learning and SARSA in that it can be either on-policy or off-policy. What sets it apart though is the emphasis on episodes. These simply are a way of batching the reinforcement learning cycle updates, that we introduced in this article, such that the updating of the Q-Values of the Q-Map happens less frequently.

With the Monte Carlo algorithm, Q-Values are only updated after the completion of an episode. An episode is a batch of cycles. For this article, we have assigned this number of cycles the input parameter ‘m_episodes_size’ and it is optimizable or adjustable. Monte Carlo is attributed to being quite robust to market variability because it can better simulate a wide range of possible market scenarios, allowing traders to determine how different strategies perform under a variety of conditions. This variability helps traders understand potential tradeoffs, risks and returns, enabling them to make more informed decisions.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 46): Ichimoku

The Ichimoku Kinko Hyo, that is often referred to as the Ichimoku Cloud, is a wide-embracing technical analysis system designed to provide a holistic view of market trends; support and resistance levels; as well as momentum. Developed in the late 1930s and refined over the subsequent three decades, Ichimoku Kinko Hyo translates from Japanese to "one-look equilibrium chart" or "at-a-glance balance chart,"; names which emphasize its design to offer a single, detailed perspective on the market.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 48): Bill Williams Alligator

The Alligator indicator, that was developed by Bill Williams with the premise that markets tend to trend strongly in any set direction for only about 15 – 30% of the time. It inherently is a trend following tool that helps traders identify market direction and potential fractals or turning points. This it achieves by using a set of three smoothed moving averages (SMAs) that are not only set at different averaging periods, but are also shifted forward by varying amounts.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 47): Reinforcement Learning with Temporal Difference

The introduction to temporal difference (TD) learning in reinforcement learning serves as a gateway to understand how TD distinguishes itself from other algorithms, such as Monte Carlo, Q-Learning, and SARSA. This article aims to unravel the complexities surrounding TD learning by highlighting its unique ability to update value estimates incrementally based on partial information from episodes, rather than waiting for episodes to complete as seen in Monte Carlo methods. This distinction makes TD learning a powerful tool, especially where environments are dynamic and require prompt updates to the learning policy.

In the last reinforcement-learning article, we looked at the Monte Carlo algorithm that gathered reward information over multiple cycles before performing a single update for each episode. Temporal difference (TD) though, is all about learning from partial and incomplete episodes much like the algorithms of Q-Learning and SARSA that we tackled earlier on here and here.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 49): Reinforcement Learning with Proximal Policy Optimization

We continue our series on the MQL5 wizard, where lately we are alternating between simple patterns from common indicators and reinforcement learning algorithms. Having considered indicator patterns (Bill Williams’ Alligator) in the last article, we now return to reinforcement learning, where this time the algorithm we are looking at is Proximal Policy Optimization (PPO). It is reported that this algorithm, that was first published 7 years ago, is the reinforcement-learning algorithm of choice for ChatGPT. So, clearly there is some hype surrounding this approach to reinforcement learning. The PPO algorithm is intent on optimizing the policy (the function defining the actor’s actions) in a way that improves overall performance by preventing drastic changes that could make the learning process unstable.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 50): Awesome Oscillator

The awesome oscillator is another indicator that was developed by the legendary investor Bill Williams, besides the Alligator that we considered in the last indicator-pattern article. In principle, it is designed to measure market momentum and help pinpoint potential changes in prevalent trends.