Enregistré dans:
Détails bibliographiques
Auteurs principaux: Khelifi, Elouanes, Saki, Amir, Faghihi, Usef
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.23424
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911234860777472
author Khelifi, Elouanes
Saki, Amir
Faghihi, Usef
author_facet Khelifi, Elouanes
Saki, Amir
Faghihi, Usef
contents Deep Q Networks (DQN) have shown remarkable success in various reinforcement learning tasks. However, their reliance on associative learning often leads to the acquisition of spurious correlations, hindering their problem-solving capabilities. In this paper, we introduce a novel approach to integrate causal principles into DQNs, leveraging the PEACE (Probabilistic Easy vAriational Causal Effect) formula for estimating causal effects. By incorporating causal reasoning during training, our proposed framework enhances the DQN's understanding of the underlying causal structure of the environment, thereby mitigating the influence of confounding factors and spurious correlations. We demonstrate that integrating DQNs with causal capabilities significantly enhances their problem-solving capabilities without compromising performance. Experimental results on standard benchmark environments showcase that our approach outperforms conventional DQNs, highlighting the effectiveness of causal reasoning in reinforcement learning. Overall, our work presents a promising avenue for advancing the capabilities of deep reinforcement learning agents through principled causal inference.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causal Deep Q Network
Khelifi, Elouanes
Saki, Amir
Faghihi, Usef
Artificial Intelligence
Deep Q Networks (DQN) have shown remarkable success in various reinforcement learning tasks. However, their reliance on associative learning often leads to the acquisition of spurious correlations, hindering their problem-solving capabilities. In this paper, we introduce a novel approach to integrate causal principles into DQNs, leveraging the PEACE (Probabilistic Easy vAriational Causal Effect) formula for estimating causal effects. By incorporating causal reasoning during training, our proposed framework enhances the DQN's understanding of the underlying causal structure of the environment, thereby mitigating the influence of confounding factors and spurious correlations. We demonstrate that integrating DQNs with causal capabilities significantly enhances their problem-solving capabilities without compromising performance. Experimental results on standard benchmark environments showcase that our approach outperforms conventional DQNs, highlighting the effectiveness of causal reasoning in reinforcement learning. Overall, our work presents a promising avenue for advancing the capabilities of deep reinforcement learning agents through principled causal inference.
title Causal Deep Q Network
topic Artificial Intelligence
url https://arxiv.org/abs/2510.23424