M Nie, D Chen, D Wang - IEEE Transactions on Emerging …, 2023 - ieeexplore.ieee.org
… on graphstructured environments. We show the times cited and publications over time of Graph ReinforcementLearning … 1 to prove the fusion of graph mining methods with RL for graph-…
… reveal that the proposed method marginally outperforms S2V-DQN and scales to much larger graph instances up to 100000 nodes. In addition, it is significantly more efficient in terms of …
X Zhao, C Wu - IEEE Transactions on Network and Service …, 2021 - ieeexplore.ieee.org
… avoidance, we adopt a multiagent reinforcementlearning (MARL) model to schedule DL … We design a hierarchical Graph Neural Network (GNN) with edge information encoded to …
… We introduce Inductive GraphReinforcementLearning (IG-RL) based on graph-convolutional networks which adapts to the structure of any road network, to learn detailed …
… This makes it hard to learn abstract representations of mutual … graph convolutional reinforcementlearning, where graph convolution adapts to the dynamics of the underlying graph of …
W Zheng, D Wang, F Song - ACM Transactions on Parallel Computing, 2023 - dl.acm.org
… learning good heuristics to solve graph optimization problems. However, the existing RL systems either do not support graph RL … of reinforcementlearning in solving large-scale graph …
… As a first contribution, we show the benefits of a feedback graph in achieving more favorable learning guarantees for optimistic model-based algorithms. Algorithms in this family, such …
… Machine Learning (ML), an increasingly important tool for combinatorial optimisation (Bengio et al., 2021). Concretely, we opt for ReinforcementLearning (RL), a framework for learning …
B Wu, L Li - Information Sciences, 2022 - Elsevier
… and inspired by the reinforcementlearning techniques, we … the MWM problem on large-scale general graphs. First, since … edge-selection on large-scale graphs, we propose an edge-…