L Wen, X Li, L Gao - IEEE Transactions on Industrial Electronics, 2020 - ieeexplore.ieee.org
… develop a novel learning rate scheduler based on the reinforcementlearning (RL) for convolutional neuralnetwork (RL-CNN) in fault classification, which can schedule the learning rate …
CF Touzet - Robotics and Autonomous Systems, 1997 - Elsevier
… In this paper, we have presented the results of research aimed at improving reinforcement learning through the use of neuralnetwork implementations. The same real robot, …
BQ Huang, GY Cao, M Guo - … conference on machine learning …, 2005 - ieeexplore.ieee.org
… reinforcementlearningneuralnetwork is proposed in this paper. Q-learning is one kind of reinforcementlearning method that is similar to dynamic programming and the neuralnetwork …
R Lu, SH Hong, M Yu - IEEE Transactions on Smart Grid, 2019 - ieeexplore.ieee.org
… prediction model based on artificial neural network is presented. In cooperation with forecasted future prices, multi-agent reinforcementlearning is adopted to make optimal decisions for …
… algorithm is called Deep ReinforcementLearning (DRL) (29). … state representation and reinforcementlearning. Depending … layer Artificial NeuralNetworks with ReinforcementLearning …
Deep NeuralNetworks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN …
… Deep learning (DL) and reinforcementlearning (RL) … in the “Deep Learning and Reinforcement Learning” session of … advances of deep learning and reinforcementlearning algorithms. …
… This work proposes a novel real-time incentive-based DR program with reinforcement learning (RL) and deep neuralnetwork (DNN) in a hierarchical electricity market, aiming to help …
… reinforcementlearning [20], have demonstrated how by using a Convolutional NeuralNetwork (… Inspired by these findings, this work applies deep reinforcementlearning to the setting of …