Search Results for author: Shih-wei Liao

Found 5 papers, 2 papers with code

Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning

1 code implementation6 Feb 2021 Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu, Shih-wei Liao

Multi-Agent Reinforcement Learning (MARL) has seen revolutionary breakthroughs with its successful application to multi-agent cooperative tasks such as computer games and robot swarms.

SMAC Starcraft

QR-MIX: Distributional Value Function Factorisation for Cooperative Multi-Agent Reinforcement Learning

no code implementations9 Sep 2020 Jian Hu, Seth Austin Harding, Haibin Wu, Siyue Hu, Shih-wei Liao

Existing methods such as Value Decomposition Network (VDN) and QMIX estimate the value of long-term returns as a scalar that does not contain the information of randomness.

SMAC Starcraft

An Uncoupled Training Architecture for Large Graph Learning

no code implementations21 Mar 2020 Dalong Yang, Chuan Chen, Youhao Zheng, Zibin Zheng, Shih-wei Liao

Instead of directly processing the coupled nodes as GCNs, Node2Grids supports a more efficacious method in practice, mapping the coupled graph data into the independent grid-like data which can be fed into the efficient Convolutional Neural Network (CNN).

Graph Learning

RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes

2 code implementations ICCV 2019 Po-Wei Wu, Yu-Jing Lin, Che-Han Chang, Edward Y. Chang, Shih-wei Liao

Our method is capable of modifying images by changing particular attributes of interest in a continuous manner while preserving the other attributes.

Image-to-Image Translation

An Evaluation of Bitcoin Address Classification based on Transaction History Summarization

no code implementations19 Mar 2019 Yu-Jing Lin, Po-Wei Wu, Cheng-Han Hsu, I-Ping Tu, Shih-wei Liao

Bitcoin is a cryptocurrency that features a distributed, decentralized and trustworthy mechanism, which has made Bitcoin a popular global transaction platform.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.