Review for NeurIPS paper: An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch

Summary: This paper proposes a new technique for learning to transfer optimal policies obtained from a simulator to a real world environment. The only difference between sim and real is in the state transition probabilities. The main idea consists in learning an action grounding function that maps state-actions learned in simulation to modified actions that are executed in the real system. The authors notice that this problem is similar to a variant of imitation learning, where the imitator learns to match state trajectories (where the actions are unknown) demonstrated by an expert. Experiments on MuJoCO where the "real" environment is obtained by modifying physical properties (such as mass and friction) from their values in simulation.