Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

Understand

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering.

• Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating human feedback, i.e.
• teacher's preferences between two clips of behaviors.
• However, poor feedback-efficiency still remains a problem in current preference-based RL algorithms, as tailored human feedback is very expensive.