Safe Deep RL in 3D Environments using Human Feedback. (arXiv:2201.08102v1 [cs.LG])

Agents should avoid unsafe behaviour during both training and deployment.
This typically requires a simulator and a procedural specification of unsafe
behaviour. Unfortunately, a simulator is not always available, and procedurally
specifying constraints can be difficult or impossible for many real-world
tasks. A recently introduced technique, ReQueST, aims to solve this problem by
learning a neural simulator of the environment from safe human trajectories,
then using the learned simulator to efficiently learn a reward model from human
feedback. However, it …

3d arxiv deep rl human rl