Misspecification in Inverse Reinforcement Learning

Understand

The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$.

• To do this, we need a model of how $\pi$ relates to $R$.
• In the current literature, the most common models are optimality, Boltzmann rationality, and causal entropy maximisation.
• One of the primary motivations behind IRL is to infer human preferences from human behaviour.