Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies release_ah3zmprekrf35bive6zatnrgxi

by Jeong-Hoon Lee, Jongeun Choi

Released as a article .

2022  

Abstract

Deep reinforcement learning has shown its effectiveness in various applications, providing a promising direction for solving tasks with high complexity. However, naively applying classical RL for learning a complex long-horizon task with a single control policy is inefficient. Thus, policy modularization tackles this problem by learning a set of modules that are mapped to primitives and properly orchestrating them. In this study, we further expand the discussion by incorporating simultaneous activation of the skills and structuring them into multiple hierarchies in a recursive fashion. Moreover, we sought to devise an algorithm that can properly orchestrate the skills with different action spaces via multiplicative Gaussian distributions, which highly increases the reusability. By exploiting the modularity, interpretability can also be achieved by observing the modules that are used in the new task if each of the skills is known. We demonstrate how the proposed scheme can be employed in practice by solving a pick and place task with a 6 DoF manipulator, and examine the effects of each property from ablation studies.
In text/plain format

Archived Files and Locations

application/pdf  6.3 MB
file_z6ocjx2qcrgepkvjct3ympne6m
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-06-14
Version   v4
Language   en ?
arXiv  2110.01833v4
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: ab710d5a-fe2b-4ee5-8617-6677606f7bd2
API URL: JSON