27 points | by daww 4 days ago ago
4 comments
Hi HN, Andrea (the author) here.
This is the last post of my series on quadcopter simulation and (Reinforcement Learning based) control.
This post is less educational that the other ones and more like a recipe, hope it'll be useful/interesting for others too!
I was glad to see it's a simulated environment. Otherwise, RL'ing your way to drone supremacy is going to get really expensive.
haha definitely, PPO is not the most sample efficient method for sure
Only one million crashes until it learns to hover, lol
Hi HN, Andrea (the author) here.
This is the last post of my series on quadcopter simulation and (Reinforcement Learning based) control.
This post is less educational that the other ones and more like a recipe, hope it'll be useful/interesting for others too!
I was glad to see it's a simulated environment. Otherwise, RL'ing your way to drone supremacy is going to get really expensive.
haha definitely, PPO is not the most sample efficient method for sure
Only one million crashes until it learns to hover, lol