GUIDE: Real-Time Human-Shaped Agents

TL;DR

GUIDE introduces a real-time human-guided reinforcement learning framework that accelerates policy learning by leveraging continuous human feedback and a simulated feedback module, demonstrating significant improvements in success rates on challenging tasks.

Contribution

The paper presents GUIDE, a novel framework combining real-time human guidance with a simulated feedback module to enhance reinforcement learning efficiency and reduce human input requirements.

Findings

Up to 30% increase in success rate with 10 minutes of human feedback

Effective learning on tasks with sparse rewards and visual inputs

Simulated feedback reduces human effort while maintaining performance

Abstract

The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and sparse learning signals remain challenging. One way of improving the learning speed and performance of these agents is to leverage human guidance. In this work, we introduce GUIDE, a framework for real-time human-guided reinforcement learning by enabling continuous human feedback and grounding such feedback into dense rewards to accelerate policy learning. Additionally, our method features a simulated feedback module that learns and replicates human feedback patterns in an online fashion, effectively reducing the need for human input while allowing continual training. We demonstrate the performance of our framework on challenging tasks with sparse rewards and visual observations. Our human study involving 50 subjects offers strong quantitative and qualitative evidence of the effectiveness of our approach. With only 10 minutes of human feedback, our algorithm achieves up to 30% increase in success rate compared to its RL baseline.