Causal Imitation Learning under Temporally Correlated Noise
Abstract
We develop algorithms for imitation learning from policy data that was corrupted by temporally correlated noise in expert actions. When noise affects multiple timesteps of recorded data, it can manifest as spurious correlations between states and actions that a learner might latch on to, leading to poor policy performance. To break up these spurious correlations, we apply modern variants of the instrumental variable regression (IVR) technique of econometrics, enabling us to recover the underlying policy without requiring access to an interactive expert. In particular, we present two techniques, one of a generative-modeling flavor (DoubIL) that can utilize access to a simulator, and one of a game-theoretic flavor (ResiduIL) that can be run entirely offline. We find both of our algorithms compare favorably to behavioral cloning on simulated control tasks.
BibTeX
@conference{Swamy-2022-133114,author = {Gokul Swamy and Sanjiban Choudhury and J. Andrew Bagnell and Zhiwei Steven Wu},
title = {Causal Imitation Learning under Temporally Correlated Noise},
booktitle = {Proceedings of (ICML) International Conference on Machine Learning},
year = {2022},
month = {August},
keywords = {causal inference imitation learning},
}