Thank you . How do you prevent the model from overfitting to the rule-based labels, and can it eventually discover strategies that outperform the original rules?
How do you train your model? Does it learn through self-play?
I’m really glad I found it.
Thank you . How do you prevent the model from overfitting to the rule-based labels, and can it eventually discover strategies that outperform the original rules?
How do you train your model? Does it learn through self-play?
I’m really glad I found it.