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.
@article{arxiv.2201.09635,
title = {State-Conditioned Adversarial Subgoal Generation},
author = {Vivienne Huiling Wang and Joni Pajarinen and Tinghuai Wang and Joni-Kristian Kämäräinen},
journal= {arXiv preprint arXiv:2201.09635},
year = {2023}
}