SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Yongyan, Li, Siyuan, Zuo, Rongchang, Yuan, Lei, Mao, Hangyu, Liu, Peng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913153484324864
author Wen, Yongyan
Li, Siyuan
Zuo, Rongchang
Yuan, Lei
Mao, Hangyu
Liu, Peng
author_facet Wen, Yongyan
Li, Siyuan
Zuo, Rongchang
Yuan, Lei
Mao, Hangyu
Liu, Peng
contents Deep reinforcement learning (DRL) has achieved remarkable success in various research domains. However, its reliance on neural networks results in a lack of transparency, which limits its practical applications. To achieve explainability, decision trees have emerged as a popular and promising alternative to neural networks. Nonetheless, due to their limited expressiveness, traditional decision trees struggle with high-dimensional long-horizon continuous control tasks. In this paper, we proposes SkillTree, a novel framework that reduces complex continuous action spaces into discrete skill spaces. Our hierarchical approach integrates a differentiable decision tree within the high-level policy to generate skill embeddings, which subsequently guide the low-level policy in executing skills. By making skill decisions explainable, we achieve skill-level explainability, enhancing the understanding of the decision-making process in complex tasks. Experimental results demonstrate that our method achieves performance comparable to skill-based neural networks in complex robotic arm control domains. Furthermore, SkillTree offers explanations at the skill level, thereby increasing the transparency of the decision-making process.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12173
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
Wen, Yongyan
Li, Siyuan
Zuo, Rongchang
Yuan, Lei
Mao, Hangyu
Liu, Peng
Machine Learning
Artificial Intelligence
Deep reinforcement learning (DRL) has achieved remarkable success in various research domains. However, its reliance on neural networks results in a lack of transparency, which limits its practical applications. To achieve explainability, decision trees have emerged as a popular and promising alternative to neural networks. Nonetheless, due to their limited expressiveness, traditional decision trees struggle with high-dimensional long-horizon continuous control tasks. In this paper, we proposes SkillTree, a novel framework that reduces complex continuous action spaces into discrete skill spaces. Our hierarchical approach integrates a differentiable decision tree within the high-level policy to generate skill embeddings, which subsequently guide the low-level policy in executing skills. By making skill decisions explainable, we achieve skill-level explainability, enhancing the understanding of the decision-making process in complex tasks. Experimental results demonstrate that our method achieves performance comparable to skill-based neural networks in complex robotic arm control domains. Furthermore, SkillTree offers explanations at the skill level, thereby increasing the transparency of the decision-making process.
title SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.12173