Imitation-Learning-Covariate-Shift-Risk-Dataset

This dataset simulates covariate shift, the central failure mode of imitation learning: a behavior-cloned policy accumulates small per-step errors that drift it off the expert's demonstrated states, compounding quadratically over the rollout horizon, a bound Ross and Bagnell (2010) prove and Rajaraman et al (2020) show is an unavoidable information-theoretic lower bound. DAgger fixes this by querying the expert on states the current policy visits, reducing the bound to linear. The simulation spans 1920 configurations across five India-relevant tasks including autonomous e-rickshaw driving and agri-robot weeding. Ten grounding sources are documented in imitation_theory.py and the README Research basis.