Reinforcement learning is a powerful tool that lets us solve difficult problems, from playing Go well to have self driving cars. RL algorithms start by defining and environment that simulate the problem we want to solve and some kind of reward that correlate with success. Afterwards the program ”plays” the environment trying to get the maximum reward and using various algorithms it learns from past mistakes. One of the main problems with using RL is that many environments, such as self driving cars or fine tuning a chat bot, require a carefully crafted reward function based on many heuristics. Those environments often has an expert (usually a human) that intuitively knows the environment. In this project we will analyze and imitate this expert given a set of choices (transitions) it makes using Inverse Reinforcement Learning tools. We would use GAN based method to generate the underlying reward function explaining the expert, and train a policy on said reward function. We proposed a learnt measure between the expert and other policy that capture the intent of the expert regardless of the RL algorithm or reward function they were trained on.