Claude started in Shocklab during his Honours when he did the reading module on Reinforcement Learning. This course kicked off what would become a 6 year long journey studying Reinforcement Learning all the way to the PhD level. Claude’s PhD research was on Multi-Agent Reinforcement Learning and how to leverage diverse pre-collected datasets of experience to improve learning. During his PhD he published several times at top tier venues including NeurIPS, ICML and ICLR. Claude now works in industry as an AI Research Engineer, but remains active in Shocklab by giving talks on RL and co-supervising research projects.