Using NEAT/RL/DL for trading?

Hi everyone,

This time, I thought of discussing possibilities of trading with neural nets. So this thread is mainly for discussion with people that do know a bit about deep and/or reinforcement learning, although all opinions are welcome.

I recently stumbled upon these two very mysterious (obviously) YouTube channels that seem to use some sort of neuro-evolution of augmented topologies (or NEAT for short) for trading purposes. I myself tried to create a small experiment in Python but so far, I did not quite get the results I was looking for.
Basically, the way I laid out the experiment is the following:

1. I used EURUSD hourly data from past N years (let's say 5), that I split into training (80 first percent of the data) and testing (remaining 20%).
2. I considered that at each moment, the agent has the info on the given closing price delta, trend/indicators data, and also its own state information (in or out of position, current P/L, current holding time, etc.). I also tried variants of "handmade RNN structure" where the current input also has info on the past states of the market and the agent.
3. I took into account expected spreads and swaps for holding.
4. I made a small logic where the input at each time step is as detailed above, and the output is a softmax on four possibilities: buy, sell, hold, close. The output is then interpreted to take action and apply corresponding changes to the agent's performance.
5. I then run thousands of generations with different types of settings on NEAT on this experiment, using final P/L as a fitness function (although I tweaked it a bit to force the agent to be active and not just go long because the EURUSD went up, by setting: fitness = P/L * log(#long_trades) * log(#short_trades) for example). Other fitness functions such as Sharpe ratios or custom mean/deviation measures could be interesting here too...

Anyone here tried similar stuff? I'm talking deep/reinforcement learning, genetic evolutionary algorithms, or even stochastic control theory? I'd be super happy to discuss and possibly find out/share interesting things.

Link #1: see the video and the channel for more examples

Link #2: another interesting video:


Cheers,
m10021

Anyone? Thoughts on this?

I do. I messaged you

I tried, and trying right now.. im starting to learn this NEAT algorythm but its difficult to get all this data to the input.
We dont need a user interface like this..
Watch the second video, this im trying to do since 2 weeks , but im not able to accomplished.

High-Frequency Trading Model (Sped Up)

Hi,
Interesting, but doesn't your ea take to many trades? It took me about 6 months to program NEAT from scratch in mql5. Since a few days I have a working version (almost 4000 lines of code). It creates 200 bots (adjustable). It evaluates their quality (fitness) and eliminates the bad ones (fitness<fitnessthreshold), than groups (k-means) calculates qty and creates offspring. It applies the mutation-rules.
I am getting some very impressive results. The ea allways kills/recreates bots to continually improve. I have seen bots that did as well as a profit to loss ratio of 3-3.5 over 200 epochs (1 epoch = 1/3 of a day). It is now time for extensive testing on a testing account to verify the results. Very Promissing but it was a huge amount of work. (since bing chat ai, things did speed up quite a bit).

I find it cool how you dared to implement this in mql5, what's the performance like? I would be happy to see some results when you have them.