c/artificial_intel · by Wilshire@lemmy.ml · 2yChampion-level Drone Racing using Deep Reinforcement Learning (Nature, 2023) https://youtu.be/fBiataDpGIo18 points · 1 comments · view on lemmy.world
1 Comments
phario@lemmy.ca · 2 pts · 2y
It was a bit unclear to me how stable this was to adjusting the course. Did they set up the course in a blind fashion?
With a lot of ML it boils down to how well the training set represents the situation.