Encyclopedia · 176 concepts

Reinforcement Learning · advanced · concept 130 of 176

Inverse Reinforcement Learning

Learning the reward function from observing expert behavior, inferring WHAT the expert is optimizing, not just imitating their actions. Key for building AI that understands human preferences.

Key terms

Reward inferenceExpert demonstrationsImitation learningIRL

Guides and articles

CS 185/285

Berkeley CS285

Courses, papers, and more