Young M Lee — accepted AI-conference papers

2022

MDPGT: Momentum-Based Decentralized Policy Gradient Tracking

Zhanhong Jiang, Xian Yeow Lee, Sin Yong Tan, Kai Liang Tan, Aditya Balu, Young M Lee +2

AAAI 2022technical

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momen…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2021

Decentralized Deep Learning Using Momentum-Accelerated Consensus

Aditya Balu, Zhanhong Jiang, Sin Yong Tan, Chinmay Hegde, Young M. Lee, Soumik Sarkar

ICASSP 2021accepted

We consider the problem of decentralized deep learning where multiple agents collaborate to learn from a distributed dataset. While several decentralized deep learning approaches exist, the majority consider a central parameter-server topology for aggregating the model parameters from the agents. Ho…

Cited by 0 Source ↗Scholar ↗