State-Conditioned Adversarial Subgoal Generation

TL;DR

This paper introduces a hierarchical reinforcement learning method that uses adversarial training to generate compatible subgoals, addressing non-stationarity issues and improving learning efficiency in continuous control tasks.

Contribution

It presents a novel adversarial approach for high-level subgoal generation that adapts to the current low-level policy, enhancing HRL performance.

Findings

Improves learning efficiency in continuous control tasks.

Enhances HRL performance compared to state-of-the-art methods.

Mitigates non-stationarity in off-policy HRL.

Abstract

Hierarchical reinforcement learning (HRL) proposes to solve difficult tasks by performing decision-making and control at successively higher levels of temporal abstraction. However, off-policy HRL often suffers from the problem of a non-stationary high-level policy since the low-level policy is constantly changing. In this paper, we propose a novel HRL approach for mitigating the non-stationarity by adversarially enforcing the high-level policy to generate subgoals compatible with the current instantiation of the low-level policy. In practice, the adversarial learning is implemented by training a simple state-conditioned discriminator network concurrently with the high-level policy which determines the compatibility level of subgoals. Comparison to state-of-the-art algorithms shows that our approach improves both learning efficiency and performance in challenging continuous control tasks.