Skip to main content

Invariant Adversarial Imitation Learning from Visual Inputs

Haoran Zhang (East China Normal university); Yinghong Tian (East China Normal University); Liang Yuan (Beijing University of Chemical Technology); Yue Lu (East China Normal University)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
06 Jun 2023

Generalization across environments is critical when using imitation learning algorithms in real-world applications. In this paper, we propose an invariant model-based adversarial imitation learning (IMAIL) method to improve generalization. IMAIL develops a variational dynamics model providing rich auxiliary objectives for efficiently learning compact state representations. The latent representations are then regularized using mutual information constraints, guaranteeing that they are insensitive to environmental changes. Based on such representations, we utilize model-based adversarial imitation learning to mimic expert behavior in the latent space. As a result, the learned policies are well generalized in unseen environments. We conduct experiments with several vision-based control tasks to demonstrate the performance of IMAIL. Experimental results show that IMAIL significantly outperforms existing baselines and successfully achieves expert-level performance in all unseen test environments.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00