Energy-efficient mobile crowdsensing by unmanned vehicles: A sequential deep reinforcement learning approach

C Piao, CH Liu - IEEE Internet of Things Journal, 2019 - ieeexplore.ieee.org
… to enable human participants to use their equipped mobile devices to collected data. And …
which used sensors on vehicles rather than human participants. For example, Xiao et. al in [8] …

A deep reinforcement learning framework for continuous intraday market bidding

I Boukas, D Ernst, T Théate, A Bolland, A Huynen… - Machine Learning, 2021 - Springer
… In this paper, we focus on the sequential decision-making problem related to the optimal
operation of a storage device participating in the CID market. Firstly, we present a novel …

Deep reinforcement learning multi-agent system for resource allocation in industrial internet of things

J Rosenberger, M Urlaub, F Rauterberg, T Lutz, A Selig… - Sensors, 2022 - mdpi.com
… The network consists of a large number of participants, primarily industrial edge devices like
… This means the participants have a variable number of linkages between each other but …

Experience-driven computational resource allocation of federated learning by deep reinforcement learning

Y Zhan, P Li, S Guo - 2020 IEEE International Parallel and …, 2020 - ieeexplore.ieee.org
… As shown in Figure 8, with more mobile devices participating in the federated learning,
our DRL-based approach can also obtain the best performance as compared with the state-ofthe-…

Reinforcement learning-based device scheduling for renewable energy-powered federated learning

Y Cui, K Cao, T Wei - IEEE Transactions on Industrial …, 2022 - ieeexplore.ieee.org
… Obviously, energy has become a crucial factor restricting the performance of IoT devices,
especially for IoT devices participating in FL training. Nowadays, harvesting renewable energy (…

Evaluating participant responses to a virtual reality experience using reinforcement learning

J Llobera, A Beacco, R Oliva… - Royal Society …, 2021 - royalsocietypublishing.org
… whereby there is an underlying reinforcement learning (RL) agent that presents binary
options for a change on one particular factor at a time to participants at regular time intervals. …

[HTML][HTML] Encouraging physical activity in patients with diabetes: intervention using a reinforcement learning system

E Yom-Tov, G Feraru, M Kozdoba, S Mannor… - Journal of medical …, 2017 - jmir.org
… results show that participants who received messages generated by the learning algorithm
… not require patients to maintain a separate device to participate in the experiment. It also has …

Auxiliary-task based deep reinforcement learning for participant selection problem in mobile crowdsourcing

W Shen, X He, C Zhang, Q Ni, W Dou… - Proceedings of the 29th …, 2020 - dl.acm.org
… With the massive deployment of mobile devices, mobile crowdsourcing (MCS) has become
… features from participants and tasks, and the pointer network to select suitable participants to …

Multiagent reinforcement learning meets random access in massive cellular internet of things

J Bai, H Song, Y Yi, L Liu - IEEE Internet of Things Journal, 2021 - ieeexplore.ieee.org
… IPS, we design a novel reinforcement learning structure, named branching actor–… device
i as a participating device at the tth RAO. The CH will select K devices as participating devices

Trust-augmented deep reinforcement learning for federated learning client selection

G Rjoub, OA Wahab, J Bentahar, R Cohen… - Information Systems …, 2022 - Springer
… machine learning model on their devices … to participate in the training of a certain task. In
this paper, we address this challenge and propose a trust-based deep reinforcement learning