Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control

TL;DR

This paper introduces a novel hierarchical imitation learning algorithm that uses adversarial inverse reinforcement learning, EM, and a directed information term to recover hierarchical policies from unannotated demonstrations in robotic control tasks.

Contribution

It develops an end-to-end hierarchical imitation learning method incorporating causal modeling and variational autoencoders, improving policy recovery from unannotated data.

Findings

Outperforms existing methods on robotic control tasks

Enhances causality in hierarchical policy learning

Provides theoretical justifications for the approach

Abstract

Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy with the option framework. Existing methods either overlook the causal relationship between the subtask and its corresponding policy or cannot learn the policy in an end-to-end fashion, which leads to suboptimality. In this work, we develop a novel HIL algorithm based on Adversarial Inverse Reinforcement Learning and adapt it with the Expectation-Maximization algorithm in order to directly recover a hierarchical policy from the unannotated demonstrations. Further, we introduce a directed information term to the objective function to enhance the causality and propose a Variational Autoencoder framework for learning with our objectives in an end-to-end fashion. Theoretical justifications and evaluations on challenging robotic control tasks are provided to show the superiority of our algorithm. The codes are available at https://github.com/LucasCJYSDL/HierAIRL.