… to train neural networks for reinforcement learning … neural network weights using genetic
algorithms. A variant of the genetic algorithm is used to optimize the weights of a neural network …

… develop a novel learning rate scheduler based on the reinforcement learning (RL) for
convolutional neural network (RL-CNN) in fault classification, which can schedule the learning rate …

… In this paper, we have presented the results of research aimed at improving reinforcement
learning through the use of neural network implementations. The same real robot, …

… reinforcement learning neural network is proposed in this paper. Q-learning is one kind of
reinforcement learning method that is similar to dynamic programming and the neural network …

… prediction model based on artificial neural network is presented. In cooperation with forecasted
future prices, multi-agent reinforcement learning is adopted to make optimal decisions for …

… algorithm is called Deep Reinforcement Learning (DRL) (29). … state representation and
reinforcement learning. Depending … layer Artificial Neural Networks with Reinforcement Learning …

Deep Neural Networks (DNNs) typically require massive amount of computation resource in
inference tasks for computer vision applications. Quantization can significantly reduce DNN …

… Deep learning (DL) and reinforcement learning (RL) … in the “Deep Learning and Reinforcement
Learning” session of … advances of deep learning and reinforcement learning algorithms. …

… This work proposes a novel real-time incentive-based DR program with reinforcement
learning (RL) and deep neural network (DNN) in a hierarchical electricity market, aiming to help …

… reinforcement learning [20], have demonstrated how by using a Convolutional Neural Network
(… Inspired by these findings, this work applies deep reinforcement learning to the setting of …