Adversarial Option-Aware Hierarchical Imitation Learning

Mingxuan Jing · Wenbing Huang · Fuchun Sun · Xiaojian Ma · Tao Kong · Chuang Gan · Lei Li

[ Abstract ] [ Livestream: Visit Reinforcement Learning 13 ] [ Paper ]
Wed 21 Jul 7:40 a.m. — 7:45 a.m. PDT
[ Paper ]

It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions. In this paper, we propose Option-GAIL, a novel method to learn skills at long horizon. The key idea of Option-GAIL is modeling the task hierarchy by options and train the policy via generative adversarial optimization. In particular, we propose an Expectation-Maximization(EM)-style algorithm: an E-step that samples the options of expert conditioned on the current learned policy, and an M-step that updates the low- and high-level policies of agent simultaneously to minimize the newly proposed option-occupancy measurement between the expert and the agent. We theoretically prove the convergence of the proposed algorithm. Experiments show that Option-GAIL outperforms other counterparts consistently across a variety of tasks.

Chat is not available.