Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric W orld K nowledge M odel ( WKM) to facilitate agent

As a prominent category of imitation learning methods, adversarial imitation learning (AIL) has garnered significant practical success powered by neural network approximation. However, existing theoretical studies on AIL are primarily limited to simplified scenarios such as tabular and linear function approximation and involve complex algorithmic designs that hinder practical implementation, highlighting a gap between theory and practice.

In such cases, using a set of expert trajectories could help to learn faster.

In all cases, we show significant improvement over baselines across a varietyofMuJoCotasks.

Task progress is intuitive and readily available task information that can guide an agent closer to the desired goal.