Explainable Reinforcement Learning via a Causal World Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Zhongwei, Ruan, Jingqing, Xing, Dengpeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909076313604096
author Yu, Zhongwei
Ruan, Jingqing
Xing, Dengpeng
author_facet Yu, Zhongwei
Ruan, Jingqing
Xing, Dengpeng
contents Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for explainable RL by learning a causal world model without prior knowledge of the causal structure of the environment. The model captures the influence of actions, allowing us to interpret the long-term effects of actions through causal chains, which present how actions influence environmental variables and finally lead to rewards. Different from most explanatory models which suffer from low accuracy, our model remains accurate while improving explainability, making it applicable in model-based learning. As a result, we demonstrate that our causal model can serve as the bridge between explainability and learning.
format Preprint
id arxiv_https___arxiv_org_abs_2305_02749
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Explainable Reinforcement Learning via a Causal World Model
Yu, Zhongwei
Ruan, Jingqing
Xing, Dengpeng
Machine Learning
Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for explainable RL by learning a causal world model without prior knowledge of the causal structure of the environment. The model captures the influence of actions, allowing us to interpret the long-term effects of actions through causal chains, which present how actions influence environmental variables and finally lead to rewards. Different from most explanatory models which suffer from low accuracy, our model remains accurate while improving explainability, making it applicable in model-based learning. As a result, we demonstrate that our causal model can serve as the bridge between explainability and learning.
title Explainable Reinforcement Learning via a Causal World Model
topic Machine Learning
url https://arxiv.org/abs/2305.02749