Using RLHF to train champion-level drone racing agents
Using RLHF to train champion-level drone racing agents
www.nature.com Champion-level drone racing using deep reinforcement learning - Nature
An autonomous system is described that combines deep reinforcement learning with onboard sensors collecting data from the physical world, enabling it to fly faster than human world champion drone pilots around a race track.
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.
0 comments