Riemannian Game Dynamics

Abstract

We study a class of evolutionary game dynamics defined by balancing a gain determined by the game's payoffs against a cost of motion that captures the difficulty with which the population moves between states. Costs of motion are represented by a Riemannian metric, i.e., a state-dependent inner product on the set of population states. The replicator dynamics and the (Euclidean) projection dynamics are the archetypal examples of the class we study. Like these representative dynamics, all Riemannian game dynamics satisfy certain basic desiderata, including positive correlation and global convergence in potential games. Moreover, when the underlying Riemannian metric satisfies a Hessian integrability condition, the resulting dynamics preserve many further properties of the replicator and projection dynamics. We examine the close connections between Hessian game dynamics and reinforcement learning in normal form games, extending and elucidating a well-known link between the replicator dyna

Stats

• citations31
• S2 citations—
• github stars0
• HF likes0
• heat score11.29
• arxiv keymertikopoulos2016riemannian

Related papers

• Neural Replicator Dynamics (2019)0.00
• The Dynamics Of Q-learning In Population Games: A Physics-inspired Continuity Equation Model (2022)0.00
• Learning In Multi-memory Games Triggers Complex Dynamics Diverging From Nash Equilibrium (2023)0.00
• The Evolutionary Dynamics Of Independent Learning Agents In Population Games (2020)0.00
• A Dynamics Perspective Of Pursuit-evasion Games Of Intelligent Agents With The Ability To Learn (2021)3.58
• Online Learning With Dynamics: A Minimax Perspective (2020)0.00
• Higher-order Uncoupled Learning Dynamics And Nash Equilibrium (2025)0.00
• Steering Control Of Payoff-maximizing Players In Adaptive Learning Dynamics (2023)2.26