A Strong Baseline for Batch Imitation Learning

Understand

Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making.

• We provide an easy-to-implement, novel algorithm for imitation learning under a strict data paradigm, in which the agent must learn solely from data collected a priori.
• This paradigm allows our algorithm to be used for environments in which safety or cost are of critical concern.
• Our algorithm requires no additional hyper-parameter tuning beyond any standard batch reinforcement learning (RL) algorithm, making it an ideal baseline for such data-strict regimes.