What is the term for the simplest form of imitation learning, in which a policy is trained with supervised learning to directly map states to an expert's demonstrated actions?
Show answer
Behavioral cloning
Behavioral cloning treats imitation as ordinary supervised learning over (state, action) pairs from expert demonstrations. Its central weakness is compounding error under distribution shift: small prediction errors push the agent into states absent from the demonstrations, where it has no guidance.
Also asked as:
- What imitation learning approach treats the problem as a standard supervised learning task where a policy learns to map states directly to an expert's actions?