Maximum Entropy Inverse Reinforcement Learning

Reinforcement learning (RL) aims to provide a framework for finding the optimal behavior of an intelligent agent acting in some environment. With the help of inverse reinforcement learning (IRL) we can try to improve our agents by recovering the behavior of an expert as a reward function, in essence using its domain knowledge for our needs. Maximum entropy IRL is a comparatively simple but clever method of solving the general IRL problem for discrete Markov decision processes.