Networked Communication For Mean-field Games With Function Approximation And Empirical Mean-field Estimation

Abstract

Recent algorithms allow decentralised agents, possibly connected via a communication network, to learn equilibria in mean-field games from a non-episodic run of the empirical system. However, these algorithms are for tabular settings: this computationally limits the size of agents' observation space, meaning the algorithms cannot handle anything but small state spaces, nor generalise beyond policies depending only on the agent's local state to so-called 'population-dependent' policies. We address this limitation by introducing function approximation to the existing setting, drawing on the Munchausen Online Mirror Descent method that has previously been employed only in finite-horizon, episodic, centralised settings. While this permits us to include the mean field in the observation for players' policies, it is unrealistic to assume decentralised agents have access to this global information: we therefore also provide new algorithms allowing agents to locally estimate the global empiric

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybenjamin2024networked

Related papers

• Networked Communication For Decentralised Agents In Mean-field Games (2023)0.00
• A Single Online Agent Can Efficiently Learn Mean Field Games (2024)0.00
• Policy Mirror Ascent For Efficient And Independent Learning In Mean Field Games (2022)0.00
• Decentralized Mean Field Games (2021)3.58
• Scalable Offline Reinforcement Learning For Mean Field Games (2024)0.00
• Population-aware Online Mirror Descent For Mean-field Games By Deep Reinforcement Learning (2024)0.00
• Mean-field Games With Finitely Many Players: Independent Learning And Subjectivity (2022)0.00
• Computing And Learning Stationary Mean Field Equilibria With Scalar Interactions: Algorithms And Applications (2025)0.00