Enregistré dans:
Détails bibliographiques
Auteurs principaux: He, Jiadong, Yu, Liang, Chen, Zhiqiang, Qiu, Dawei, Yue, Dong, Strbac, Goran, Zhang, Meng, Ye, Yujian, Wang, Yi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.00898
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909631992823808
author He, Jiadong
Yu, Liang
Chen, Zhiqiang
Qiu, Dawei
Yue, Dong
Strbac, Goran
Zhang, Meng
Ye, Yujian
Wang, Yi
author_facet He, Jiadong
Yu, Liang
Chen, Zhiqiang
Qiu, Dawei
Yue, Dong
Strbac, Goran
Zhang, Meng
Ye, Yujian
Wang, Yi
contents This letter proposes an Adversarial Inverse Reinforcement Learning (AIRL)-based energy management method for a smart home, which incorporates an implicit thermal dynamics model. In the proposed method, historical optimal decisions are first generated using a neural network-assisted Hierarchical Model Predictive Control (HMPC) framework. These decisions are then used as expert demonstrations in the AIRL module, which aims to train a discriminator to distinguish expert demonstrations from transitions generated by a reinforcement learning agent policy, while simultaneously updating the agent policy that can produce transitions to confuse the discriminator. The proposed HMPC-AIRL method eliminates the need for explicit thermal dynamics models, prior or predictive knowledge of uncertain parameters, or manually designed reward functions. Simulation results based on real-world traces demonstrate the effectiveness and data efficiency of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HMPC-assisted Adversarial Inverse Reinforcement Learning for Smart Home Energy Management
He, Jiadong
Yu, Liang
Chen, Zhiqiang
Qiu, Dawei
Yue, Dong
Strbac, Goran
Zhang, Meng
Ye, Yujian
Wang, Yi
Systems and Control
This letter proposes an Adversarial Inverse Reinforcement Learning (AIRL)-based energy management method for a smart home, which incorporates an implicit thermal dynamics model. In the proposed method, historical optimal decisions are first generated using a neural network-assisted Hierarchical Model Predictive Control (HMPC) framework. These decisions are then used as expert demonstrations in the AIRL module, which aims to train a discriminator to distinguish expert demonstrations from transitions generated by a reinforcement learning agent policy, while simultaneously updating the agent policy that can produce transitions to confuse the discriminator. The proposed HMPC-AIRL method eliminates the need for explicit thermal dynamics models, prior or predictive knowledge of uncertain parameters, or manually designed reward functions. Simulation results based on real-world traces demonstrate the effectiveness and data efficiency of the proposed method.
title HMPC-assisted Adversarial Inverse Reinforcement Learning for Smart Home Energy Management
topic Systems and Control
url https://arxiv.org/abs/2506.00898