submitted 11 months ago by hlfshell@programming.dev to c/robotics@programming.dev

0 comments fedilink hide all child comments

A cool application of RLHF (Reinforcement Learning w/ Human Feedback - the same approach as what OpenAI used to train ChatGPT).

The authors trained an agent to fly FPV drones at a level surpassing world champions.

no comments (yet)

sorted by: hot top controversial new old

there doesn't seem to be anything here

this post was submitted on 31 Aug 2023

1 points (100.0% liked)

Robotics

245 readers

33 users here now

Welcome to our Robotics community!

This is a place where you can post links and news about general robotics and share with the rest of the Fediverse.

For content specific to Robot Operating System software, checkout: !ros

Community References:

Q&A Exchanges:

Icon base by Lorc under CC BY 3.0 with modifications to add a gradient

founded 1 year ago

MODERATORS