Khanh Nguyen

Active Imitation Learning from Multiple Non-Deterministic Teachers:\n Formulation, Challenges, and Algorithms

2020 · arXiv (Cornell University)

We formulate the problem of learning to imitate multiple, non-deterministic\nteachers with minimal interaction cost. Rather than learning a specific policy\nas in standard imitation learning, the goal in this problem is to learn a\ndistribution over a …