We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, where meta-controller and controller play minimax over the mutual information objective but cooperate on maximizing expected rewards.
Cite
@article{arxiv.1906.07122,
title = {Hierarchical Soft Actor-Critic: Adversarial Exploration via Mutual Information Optimization},
author = {Ari Azarafrooz and John Brock},
journal= {arXiv preprint arXiv:1906.07122},
year = {2019}
}
Comments
Presented at the ICML 2019 workshop on Imitation, Intent, and Interaction, Long Beach, CA, USA