Adversarial Option-Aware Hierarchical Imitation Learning
arXiv:2106.05530
Abstract
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.
arXiv commentaccepted by ICML 2021
References in corpus (6)
- Data-Efficient Hierarchical Reinforcement Learning
- One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
- Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
- DAC: The Double Actor-Critic Architecture for Learning Options
- Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
- Provable Hierarchical Imitation Learning via EM