English

Hierarchical Soft Actor-Critic: Adversarial Exploration via Mutual Information Optimization

Machine Learning 2019-06-18 v1 Artificial Intelligence Information Theory math.IT Machine Learning

Abstract

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

R2 v1 2026-06-23T09:55:53.076Z