This repo contains the implementations for the graph-parameterized policy and robust imitator algorithms from the project. The codes are in the respective folders
Based on: de Haan, Pim, Dinesh Jayaraman, and Sergey Levine. "Causal Confusion in Imitation Learning." in Proc. of Advances in Neural Information Processing Systems (2019).
adapted from: https://github.com/pimdh/causal-confusion
Based on: Rezaei, Ashkan, Rizal Fathony, Omid Memarrast, and Brian Ziebart. "Fair Logistic Regression: An Adversarial Perspective." in Proc. of AAAI Conference on Artificial Intelligence (2020).
adapted from: https://github.com/arezae4/fair-logloss-classification