S Zeng, X Xu, Y Chen - 2020 IEEE 16th International …, 2020 - ieeexplore.ieee.org
… reinforcementlearning techniques. We propose a multi-agent reinforcementlearning framework for adaptiverouting in … of both the real-time Q-learning and the actor-critic methods. …
J Zhao, M Mao, X Zhao, J Zou - IEEE Transactions on Intelligent …, 2020 - ieeexplore.ieee.org
… deep reinforcementlearning (DRL) model, which is composed of an actor, an adaptive critic and a routing … The actor, based on the attention mechanism, is designed to generate routing …
T Phiboonbanakit, T Horanont, VN Huynh… - IEEE …, 2021 - ieeexplore.ieee.org
… In this paper, a new optimization model based on reinforcementlearning (RL) and a complementary tree-based regression method is proposed. In our proposed model, when the RL …
J Wu, M Fang, X Li - Wireless Personal Communications, 2018 - Springer
… adaptiverouting protocol based on reinforcementlearning (ARPRL) is proposed. Through distributed Q-Learningalgorithm… The second is hybrid ad-hoc routing, which is represented by …
… Q-learning applied for selecting the route in a wireless mesh network. 4) This paper … of reinforcementlearningalgorithms (eg, learning rates, discount factor) for improved self-learning …
… We observe that Algorithm 3 is the model-based reinforcementlearning Full Backup Algorithm … Fei, “MURAO: A multi-level routing protocol for acousticoptical hybrid underwater wireless …
DA Dugaev, IG Matveev, E Siemens… - … Conference on Actual …, 2018 - ieeexplore.ieee.org
… concept of adaptiverouting with machinelearningalgorithms, … adaptiveReinforcement Learning-based routingalgorithm, … The hybrid multi-hop routing protocols combine the first two …
Supposing at a time step t, agent i chooses to send a packet with destination s through outgoing link a to next agent j, we use ui t to denote the queue delay, and use vi t to denote the …
L Chen, B Hu, ZH Guan, L Zhao… - … Networks and Learning …, 2021 - ieeexplore.ieee.org
… on hybrid neural networks [24]–[30], the deep learning (DL) has been introduced in RL, named deep reinforcementlearning (… , agents can learnadaptiverouting policies in unknown …