Member-only story
Generative Adversarial Imitation Learning: Advantages & Limits
Differences with Reinforcement Learning and non-exhaustive list of use cases
A growing number of AI projects rely on learning a mapping between observations and actions. For strategic and technical reasons, learning from demonstrations will play a crucial role in developing several use cases (robots, video games, self-driving vehicles).
In my latest project, I had the chance to gain a solid understanding of Generative Adversarial Imitation Learning (GAIL). As part of a team, my goal was to use GAIL to help a robot predict and understand human behaviors for safety purposes.
In this article, I will explain Generative Adversarial Imitation Learning, introduce its advantages and explain the limits of this approach.
The importance of learning human decision-making strategies
As explained by several computer science researchers, “to make decisions, humans create specific rules/habits. For instance, some of us decide based on preferred routes or transit modes for transportation” (1). For this reason, it is essential for a machine to accurately mimic how humans behave in various scenarios, e.g., playing video games, etc.
