A Primer on Maximum Causal Entropy Inverse Reinforcement Learning
This is an incremental tutorial for researchers and practitioners in reinforcement learning, offering no new methods or data.
The paper provides a tutorial on Maximum Causal Entropy Inverse Reinforcement Learning, presenting a compressed derivation and key results from contemporary implementations to serve as an introductory resource and concise reference.
Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment. Maximum Causal Entropy (MCE) IRL is currently the most popular formulation of IRL, with numerous extensions. In this tutorial, we present a compressed derivation of MCE IRL and the key results from contemporary implementations of MCE IRL algorithms. We hope this will serve both as an introductory resource for those new to the field, and as a concise reference for those already familiar with these topics.