most citedExplore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds

27 citations · 27 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AI2017★ 27 cited

Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds

Zhiyu Lin, Brent Harrison, Aaron Keech +1

We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement lea…