Sub-policy Adaptation for Hierarchical Reinforcement Learning

Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-05
Main Authors: Li, Alexander C, Florensa, Carlos, Clavera, Ignasi, Abbeel, Pieter
Format: Article
Language:English
Subjects:
Algorithms
Decision making
Machine learning
Optimization
Skills
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can lead to significant sub-optimality in the transfer setting. In this work, we propose a novel algorithm to discover a set of skills, and continuously adapt them along with the higher level even when training on a new task. Our main contributions are two-fold. First, we derive a new hierarchical policy gradient with an unbiased latent-dependent baseline, and we introduce Hierarchical Proximal Policy Optimization (HiPPO), an on-policy method to efficiently train all levels of the hierarchy jointly. Second, we propose a method for training time-abstractions that improves the robustness of the obtained skills to environment changes. Code and results are available at sites.google.com/view/hippo-rl
ISSN:2331-8422