Wulong Liu

An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning

2020 · arXiv (Cornell University)

Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of …

Mathematical Challenges in Deep Learning

2023 · arXiv (Cornell University)

Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012. The size of deep models is increasing ever since, which brings new challenges to this field with applications in cell …