Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning

[Submitted on 18 Jun 2024]

View a PDF of the paper titled Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning, by Vittorio Giammarino and 2 other authors

View PDF
HTML (experimental)

Abstract:We propose C-LAIfO, a computationally efficient algorithm designed for imitation learning from videos, even in the presence of visual mismatch between agent and expert domains. We analyze the problem of imitation from expert videos with visual discrepancies, and introduce a solution for robust latent space estimation using contrastive learning and data augmentation. Provided a visually robust latent space, our algorithm performs imitation entirely within this space using off-policy adversarial imitation learning. We conduct a thorough ablation study to justify our design choices and test C-LAIfO on high-dimensional continuous robotic tasks. Additionally, we demonstrate how C-LAIfO can be combined with other reward signals to facilitate learning on a set of challenging hand manipulation tasks with sparse rewards. Our experiments show improved performance compared to baseline methods, highlighting the effectiveness and versatility of C-LAIfO. To ensure reproducibility, we provide open access to our code.