On Value Discrepancy of Imitation Learning

Understand

Imitation learning trains a policy from expert demonstrations.

• Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement learning, and GAIL via generative adversarial learning.
• In this paper, we propose a framework to analyze the theoretical property of imitation learning approaches based on discrepancy propagation analysis.
• Under the infinite-horizon setting, the framework leads to the value discrepancy of behavioral cloning in an order of O((1-\gamma)^{-2}).