Wei Qiu

I am a researcher at LightSpeed Studios, Tencent where I build game AI with Reinforcement Learning and AI. I obtained my PhD degree at the Nanyang Technological University, where I worked on multi-agent reinforcement learning (MARL) and reinforcement learning (RL). My PhD advisors are Bo An and Lana Obraztsova. I received my bachelor degree in management and master degree in software engineering at South China University of Technology in China.

During my PhD career, I have been broadly interested in reinforcement learning, multi-agent reinforcement learning, human-like AI, human-ai coordination, generalization and their applications to real-world problems, such as building real-time recommendation systems with RL and creating human-like bots in video games. I am also interested in generative AI, foundation models and embodied AI. My research goal is to create a generalist agent that can act in the world and benefit human beings.