Shangtong Zhang is a DPhil student at the University of Oxford working with Prof. Shimon Whiteson. The goal of his research is to solve sequential decision making problems in a scalable and reliable way. Currently, he focuses on off-policy and offline reinforcement learning as solution methods. His research has been published at venues like ICML, NeurIPS, and AAAI and his work won the best paper award at AAMAS. He regularly serves as the reviewer for major AI conferences such as NeurIPS, ICML, ICLR, and AAAI and several workshops such as NeurIPS deep RL workshops and offline RL workshops, and ICML RL for real-world workshops. He spent some time at Microsoft Research Montreal and DeepMind London AlphaStar team during his DPhil. Please visit https://shangtongzhang.github.io for more information.