Luke Marris portrait

Luke Marris

I am an artificial intelligence engineer and researcher. I have expertise in machine learning, optimization, deep learning, reinforcement learning, game theory and multiagent systems. In particular, I am interested in training deep reinforcement agents, at scale, in many-player mixed-motive games, with a focus on building principled learning algorthims that provably select and compute equilibria. Games are more than activities we play with our friends: any interaction between multiple self-interested players can be modelled as a game. Markets, trade negotiations, social norms, defence policy, environmental treaties, auctions, animal behaviour, and coordinated pandemic response, are all complex games. Understanding and calculating fair, stable, and rewarding solutions to games is crucial to solving many real-world problems.

Papers and Publications