MaxEnt Inverse Reinforcement Learning

The algorithm for maximum entropy inverse reinforcement learning is given as follows:

1. Initialize the parameter and gather the expert demonstrations
2. For N number of iterations:
   1. Compute the reward function
   2. Compute the policy using the value iteration with the reward function obtained in the previous step
   3. Compute the state visitation frequency using the policy obtained in the previous step
   4. Compute the gradient with respect to , that is,
   5. Update the value of as