Optimizing Bitcoin trading bot model and reward strategy to increase profitability #4
* O link do vídeo está no final desse post.
Saiba mais clicando em Robô IQ OPTION de AUTOMATIZAÇÃO de Lista de SINAIS
E conheça também sobre o Melhor Bot Para Opções Binárias 2022
Que tal um robo gratuito para IQ Option? Sistema Para IQ Option Grátis
Let’s improve our deep RL Bitcoin trading agent code to make even more money with a better reward strategy and by testing different model structures
In the last tutorial, we used deep reinforcement learning to create a Bitcoin trading agent that could beat the market. Although our agent was profitable compared to random actions, the results weren’t all that impressive, so this time we’re going to step it up and we’ll try to implement few more improvements with the reward system and we’ll test how our profitability depends on Neural Network model structure. Although, we’ll test everything with our code and of course, you’ll be able to download everything from my Github repository.
Text version tutorial:
GitHub code:
✅ Support My Channel Through Patreon:
✅ One-Time Contribution Through PayPal:
Every time I try to train your agent with your data (changed nothing in your code) I get a "error" after episode 368 –> "Fail to allocate bitmap" / Do you know the reason why this error appears and the agent stoped training?
Where can I parameter?
Really nice series, also I appreciate the effort you put into this content. One question, what is the reason that you use the np.random.choice() method when choosing to act on the NN, this results in a slightly different outcome for each training episode and not always in the way the NN would predict, as opposed to if you would always chose the highest probability from the prediction-array? Maybe to introduce variance into the training episode to see how the NN can handle it?
I came to give a how very good master
Probably better option is to add a option to short sell, sell bitcoin to earn on the down movement than to add this reward when holding and price drop? Very good video series 🙂
Hi man. The content is great! I learned some python (data analysis) basics in school but you make this look easy. Your videos, combined with my rising interest in stocks and crypto, make me want to get back into python and relearning everything I forgot. Keep up the great work, you are an underrated content creator. FYI, I don't say this because I think your videos will make me rich but I genuinely think you are achieving to teach your target audience.