Reinforcement learning is going to be my end. 😩😩😩☠️

(currently stuck at how to put images as well as a bunch of other -motor- values as input... and exactly what am I getting as output again?)

Pulling my own hair out... Ooooooof

Can I please quit?

@NoMad No.
You'll make it.
Check the output formula / equation / code.

I'm sure you'll get it.

Chill

I was in the same position a last week, and managed to succeed in the end and got the results I want.

Keep trying, take a small break from time to time, you'll make it.

Just remember, keep trying and don't give up.

Take some rests and don't quit! You'll be able to accomplish this.

Anyhow, have you seen this? Thought it would help you with your RL journey: https://openai.com/blog/...

@darkm0de lol. Seems fun. Bookmarked for when I have time to play.

@Ranchu the problem is that I'm supposedly designing the whole shebang. ¯\_(ツ)_/¯
The normal Qleaning formula doesn't apply, so probs have to adjust that, but that's hard to tell because the output is a change in image/views... Which is the "Urghhhh" point. (how to measure/threshold) Still got a lot to research on. *sigh*

I feel like I'm on a completely wrong track...