Thanks, I am happy you liked it. This Sunday I will publish the third part about how deep q-learning can be improved.

After that we will finally arrive at continues actions spaces and I will introduced policy gradient methods.

Thanks, I am happy you liked it. This Sunday I will publish the third part about how deep q-learning can be improved.

After that we will finally arrive at continues actions spaces and I will introduced policy gradient methods.

Deep Learning & AI Software Developer | MSc. Physics | Educator|