Description: Luke Marris' personal wesbite.
ce (792) ne (680) luke marris (1) n-player (1) general-sum (1) solution concepts (1) equilibrium selection (1) nash equilibrium (1) correlated equilibrium (1) coarse correlated equilibrium (1)
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 player
Senior Research Engineer, DeepMind PhD candidate, University College London Information Engineering, Masters, First Class, University of Cambridge Information Engineering, Bachelors, First Class, University of Cambridge London Papers and Publications Equilibrium-Invariant Embedding, Metric Space, and Fundamental Set of 2×2 Normal-Form Games 2023 Luke Marris , Ian Gemp, Georgios Piliouras arXiv DeepMind Embedding, Invariance, Nash Equilibrium, Correlated Equilibrium, Dimensionality Reduc
Equilibrium solution concepts of normal-form games, such as Nash equilibria, correlated equilibria, and coarse correlated equilibria, describe the joint strategy profiles from which no player has incentive to unilaterally deviate. They are widely studied in game theory, economics, and multiagent systems. Equilibrium concepts are invariant under certain transforms of the payoffs. We define an equilibrium-inspired distance metric for the space of all normal-form games and uncover a distance-preserving equilib