Provably Efficient Learning of Transferable Rewards
Alberto Maria Metelli,u00a0Giorgia Ramponi,u00a0Alessandro Concetti,u00a0Marcello Restelli
The reward function is widely accepted as a succinct, robust, and transferable representation of a task. Typical approaches, at the basis of Inverse Reinforcement Learning (IRL), leverage on expert demonstrations to recover a reward function. In this paper, we study the theoretical properties of the class of reward functions that are compatible with the expertu2019s behavior. We analyze how the limited knowledge of the expertu2019s policy and of the environment affects the reward reconstruction phase. Then, we examine how the error propagates to the learned policyu2019s performance when transferring the reward function to a different environment. We employ these findings to devise a provably efficient active sampling approach, aware of the need for transferring the reward function, that can be paired with a large variety of IRL algorithms. Finally, we provide numerical simulations on benchmark environments.
