Adversarial Counterfactual Environment Model Learning

Understand

A good model for action-effect prediction, named environment model, is important to achieve sample-efficient decision-making policy learning in many domains like robot control, recommender systems, and patients' treatment selection.

• We can take unlimited trials with such a model to identify the appropriate actions so that the costs of queries in the real world can be saved.
• It requires the model to handle unseen data correctly, also called counterfactual data.
• However, standard data fitting techniques do not automatically achieve such generalization ability and commonly result in unreliable models.