I find these two concepts confusing because I feel that imitation learning is just a 'subset' of supervised learning. But after thinking hard enough, I could not think of any difference and feel that they are the same.
Are they the same? or different from each other?
In supervised learning each data example has a label.
Imitation learning is mapping from observations to actions and is generally considered part of reinforcement learning.
The primary difference between supervised learning and reinforcement learning are when the labels / rewards are available. Reinforcement learning labels / rewards are often time delayed. In supervised learning, the labels / rewards have to be available concurrently with all the data. In reinforcement learning, the agent might make several actions before receiving a reward.
I also had the same question, but after looking at this two links: this article and this lecture I think we can say that behavioral cloning (which is the simplest way for doing imitation learning) is just normal supervised learning. But imitation learning could be associated with RL because it has other types (improvements) that involve learning while interacting with the environment like Dataset Aggregation, where you have an interactive expert that you can query for optimal actions to label observations obtained by rolling out the learned policy in the environment, and you repeat collecting the data and training the policy. This is done to mitigate the known problem of distributional drift in BC. More about it can be found here.
Even with this interactive expert, I still think it is supervised learning, but I can understand why some people might assoiciate it with RL.
