AI RESEARCH
Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
arXiv CS.LG
•
ArXi:2208.01899v2 Announce Type: replace Imitation learning learns a policy from expert trajectories. While the expert data is believed to be crucial for imitation quality, it was found that a kind of imitation learning approach, adversarial imitation learning (AIL), can have exceptional performance. With as little as only one expert trajectory, AIL can match the expert performance even in a long horizon, on tasks such as locomotion control. There are two mysterious points in this phenomenon.