H Wang, M Gu, Q Yu, Y Tao, J Li, H Fei, J Yan… - Knowledge-Based …, 2019 - Elsevier
… a common practice in service computing. With the rapid … based on DeepReinforcement Learning (DRL) for adaptive and large-… is adopted to improve reinforcement learning, which can …
L Huang, S Bi, YJA Zhang - … Transactions on Mobile Computing, 2019 - ieeexplore.ieee.org
… To further reduce the complexity, we propose an adaptive … a deepreinforcement learning-based online offloading (DROO) framework to maximize the weighted sum of the computation …
B Huang, Z Li, Y Xu, L Pan, S Wang… - … Mobile Computing, 2020 - Wiley Online Library
… a deepreinforcement learning technique to solve this problem. [20] jointly optimizes the offloading decision and computational resource allocation. In [21], a computation offloading and …
… His current research interests include deepreinforcement learning, computational intelligence, adaptive dynamic programming, autonomous driving, robotics, intelligent transportation …
… Using a deepreinforcement learning (RL) approach, we train policy networks for AMR … does it require a pre-computed training dataset. The local nature of our deep RL (DRL) allows the …
Y Li - arXiv preprint arXiv:1701.07274, 2017 - arxiv.org
… At each layer except input layer, we compute the input to each unit, as the … After computations flow forward from input to output, at output layer and each hidden layer, we can compute …
Y Tian, X Li, H Ma, X Zhang, KC Tan… - … Topics in Computational …, 2022 - ieeexplore.ieee.org
… To alleviate the dilemma, this work aims to use deepreinforcement learning to assist both the credit assignment and operator selection, where some basic concepts of reinforcement …
K Zhang, J Cao, Y Zhang - IEEE Transactions on Industrial …, 2021 - ieeexplore.ieee.org
… in a mirrored edge computing system, while distributively scheduling computation task offloading and edge resource allocation in an multiagent deepreinforcement learning approach. …
X Qiu, W Zhang, W Chen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
… With the objectives of minimizing the overall system cost and adapting to the dynamic … Furthermore, we propose adaptive n-step learning and combine deep neuroevolution with …