paper-with-me

홈 › Papers

A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments

2024-07-16 · Junlin Lu, Patrick Mannion, Karl Mason

Effective residential appliance scheduling is crucial for sustainable living. While multi-objective reinforcement learning (MORL) has proven effective in balancing user preferences in appliance scheduling, traditional MORL struggles with limited data in non-stationary residential settings characterized by renewable generation variations. Significant context shifts that can invalidate previously learned policies. To address these challenges, we extend state-of-the-art MORL algorithms with the meta-learning paradigm, enabling rapid, few-shot adaptation to shifting contexts. Additionally, we employ an auto-encoder (AE)-based unsupervised method to detect environment context changes. We have also developed a residential energy environment to evaluate our method using real-world data from London residential settings. This study not only assesses the application of MORL in residential appliance scheduling but also underscores the effectiveness of meta-learning in energy management. Our top-performing method significantly surpasses the best baseline, while the trained model saves 3.28% on electricity bills, a 2.74% increase in user comfort, and a 5.9% improvement in expected utility. Additionally, it reduces the sparsity of solutions by 62.44%. Remarkably, these gains were accomplished using 96.71% less training data and 61.1% fewer training steps.

📄 PDF Abstract BibTeX arXiv:2407.11489

Code (0)

등록된 구현이 없습니다.

Tasks

energy managementMeta-LearningMulti-Objective Reinforcement LearningScheduling

Similar Papers 제목 키워드 기반

REMEDI: REinforcement learning-driven adaptive MEtabolism modeling of primary sclerosing cholangitis DIsease progression

2023-10-02 · Chang Hu, Krishnakant V. Saboo, Ahmad H. Ali, Brian D. Juran 외

Primary sclerosing cholangitis (PSC) is a rare disease wherein altered bile acid metabolism contributes to sustained liver injury. This paper introduces REMEDI, a framework that captures bile acid dynamics and the body's…

Reinforcement Learning (RL)

A general Framework for Utilizing Metaheuristic Optimization for Sustainable Unrelated Parallel Machine Scheduling: A concise overview

2023-09-14 · Absalom E. Ezugwu

Sustainable development has emerged as a global priority, and industries are increasingly striving to align their operations with sustainable practices. Parallel machine scheduling (PMS) is a critical aspect of productio…

Metaheuristic OptimizationScheduling

Multi-objective Reinforcement Learning based approach for User-Centric Power Optimization in Smart Home Environments

2020-09-29 · Saurabh Gupta, Siddhant Bhambri, Karan Dhingra, Arun Balaji Buduru 외

Smart homes require every device inside them to be connected with each other at all times, which leads to a lot of power wastage on a daily basis. As the devices inside a smart home increase, it becomes difficult for the…

ManagementMulti-Objective Reinforcement LearningReinforcement Learning (RL)

Emergence of Implicit World Models from Mortal Agents

2024-11-19 · Kazuya Horibe, Naoto Yoshida

We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start…

Artificial LifeDomain AdaptationMeta Reinforcement Learning

Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation

2026-06-20 · Rifny Rachman, Bahrul Ilmi Nasution, Josh Tingey, Richard Allmendinger 외 arxiv

Meta-reinforcement learning is a promising approach to multi-objective optimisation because it enables rapid policy adaptation across changing environments and preference settings. However, conventional few-shot methods …

Reinforcement Learning