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

TL;DR

This paper introduces a method that combines human feedback with policy models to accelerate deep reinforcement learning in 3D virtual environments, improving robustness and efficiency.

Contribution

It extends deep reinforcement learning by modeling human feedback confidence and consistency, enabling adaptive strategies for listening, exploiting, or exploring.

Findings

Improves training speed and performance in 3D navigation tasks

Robust to highly inaccurate or intermittent human feedback

Operates effectively even without human feedback

Abstract

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 learning to model the confidence and consistency of human feedback. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy model, or explore the agent's environment. Managing the trade-off between these three strategies allows DRL agents to be robust to inconsistent or intermittent human feedback. Through experimentation using a synthetic oracle, we show that our technique improves the training speed and overall performance of deep reinforcement learning in navigating three-dimensional environments using Minecraft. We further show that our technique is robust to highly innacurate human feedback and can also operate when no human feedback is given.