Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • I was glad to see it's a simulated environment. Otherwise, RL'ing your way to drone supremacy is going to get really expensive.
  • Only one million crashes until it learns to hover, lol
  • haha definitely, PPO is not the most sample efficient method for sure
    by daww
  • 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!

    by daww
A recipe for drone racing with reinforcement learning · Birbla