Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero

• Main Authors: Abe, Kenshin, Xu, Zijian, Sato, Issei, Sugiyama, Masashi
• Format: Journal Article
• Language: English
• Published: 28.05.2019
• Subjects: Computer Science - Learning; Statistics - Machine Learning

There have been increasing challenges to solve combinatorial optimization problems by machine learning. Khalil et al. proposed an end-to-end reinforcement learning framework, S2V-DQN, which automatically learns graph embeddings to construct solutions to a wide range of problems. To improve the gener...