J Zheng, MN Kurt, X Wang - … Transactions on Neural Networks …, 2022 - ieeexplore.ieee.org
We propose a deep stochastic actor–critic algorithm with an integratednetwork … to the critic’s loss and a smaller learning rate for the shared parameters between the actor and the critic. …
J Zheng, MN Kurt, X Wang - … Conference on Artificial Neural Networks …, 2021 - Springer
… deterministic actor-critic algorithm with an integratednetwork architecture and an integrated … keeping the actor unchanged while the critic makes large errors. We reduce the number of …
J Sun, Z Zhu, H Li, Y Chai, G Qi, H Wang… - International Journal of …, 2019 - Elsevier
… this paper proposes an integratedactor-critic neural network for the … , an integratedcritic-actor neural network is proposed to … actor and criticnetworks, actor and critic neural network are …
… study of an integrated power, … actor-critic algorithm is introduced to solve the complex scheduling problem. The optimized decision-making action can be identified by the soft actor-critic …
… target network are also integrated into DDPG. … network is re-configured, In other words, on a new network environment, we need to train a new actornetwork π(·) and a new criticnetwork …
J Dong, H Wang, J Yang, X Lu, L Gao, X Zhou - IEEE Access, 2021 - ieeexplore.ieee.org
… The main contributions of this paper are as follows: 1) We describe the integrated energy system mathematical models and optimization problem of the electricity-heat-gas network as …
D Du, M Fei - Applied mathematics and computation, 2008 - Elsevier
… Finally, the output of the learning agent using actor–critic neural network is used to dynamically tune the control signal of local controller. Control simulations of different ways for a …
Y Wei, FR Yu, M Song, Z Han - IEEE Transactions on Wireless …, 2017 - ieeexplore.ieee.org
… -priority objective for network management. To relieve the energy cost for network operators and alleviate the energy burden for power grid, a promising solution is to integrate energy …
… In comparison with previous works, we propose actor-critic learning for resource allocation which can be used at different levels of disaggregated RANs. We use a reward function that …