Semi-supervised Deep Reinforcement Learning in Support of IoT and Smart City Services

Abstract

Smart services are an important element of the smart cities and the Internet of Things (IoT) ecosystems where the intelligence behind the services is obtained and improved through the sensory data. Providing a large amount of training data is not always feasible; therefore, we need to consider alternative ways that incorporate unlabeled data as well. In recent years, Deep reinforcement learning (DRL) has gained great success in several application domains. It is an applicable method for IoT and smart city scenarios where auto-generated data can be partially labeled by users' feedback for training purposes. In this paper, we propose a semi-supervised deep reinforcement learning model that fits smart city applications as it consumes both labeled and unlabeled data to improve the performance and accuracy of the learning agent. The model utilizes Variational Autoencoders (VAE) as the inference engine for generalizing optimal policies. To the best of our knowledge, the proposed model is the first investigation that extends deep reinforcement learning to the semi-supervised paradigm. As a case study of smart city applications, we focus on smart buildings and apply the proposed model to the problem of indoor localization based on BLE signal strength. Indoor localization is the main component of smart city services since people spend significant time in indoor environments. Our model learns the best action policies that lead to a close estimation of the target locations with an improvement of 23% in terms of distance to the target and at least 67% more received rewards compared to the supervised DRL model.

arXiv comment11 pages, 7 figures. Accepted for publication in IEEE Internet of Things Journal

References in corpus (7)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Playing Atari with Deep Reinforcement Learning
• Semi-Supervised Learning with Deep Generative Models
• Micro-location for Internet of Things equipped Smart Buildings
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• Language Understanding for Text-based Games Using Deep Reinforcement Learning
• Deep Reinforcement Learning with a Natural Language Action Space

Cited by in corpus (21)

• Low-latency Federated Learning and Blockchain for Edge Association in Digital Twin empowered 6G Networks
• A Review of Deep Reinforcement Learning for Smart Building Energy Management
• Enabling Cognitive Smart Cities Using Big Data and Machine Learning: Approaches and Challenges
• Federated Reinforcement Learning: Techniques, Applications, and Open Challenges
• The Deep Learning Compiler: A Comprehensive Survey
• Five Facets of 6G: Research Challenges and Opportunities
• Deep Reinforcement Learning (DRL): Another Perspective for Unsupervised Wireless Localization
• Decentralized Federated Learning via Mutual Knowledge Transfer
• Deep Learning Methods for Fingerprint-Based Indoor Positioning: A Review
• DQLEL: Deep Q-Learning for Energy-Optimized LoS/NLoS UWB Node Selection
• Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
• Learning to Estimate Without Bias
• OutFin, a multi-device and multi-modal dataset for outdoor localization based on the fingerprinting approach
• Improving the Performance of Deep Learning for Wireless Localization
• DeepBLE: Generalizing RSSI-based Localization Across Different Devices
• Deep Smartphone Sensors-WiFi Fusion for Indoor Positioning and Tracking
• Energy Aware Deep Reinforcement Learning Scheduling for Sensors Correlated in Time and Space
• Encrypted Value Iteration and Temporal Difference Learning over Leveled Homomorphic Encryption
• Using Deep Q-learning To Prolong the Lifetime of Correlated Internet of Things Devices
• Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT
• EdgeLoc: An Edge-IoT Framework for Robust Indoor Localization Using Capsule Networks