Networked Communication For Decentralised Agents In Mean-field Games

Abstract

Methods like multi-agent reinforcement learning struggle to scale with growing population size. Mean-field games (MFGs) are a game-theoretic approach that can circumvent this by finding a solution for an abstract infinite population, which can then be used as an approximate solution for the \(N\)-agent problem. However, classical mean-field algorithms usually only work under restrictive conditions. We take steps to address this by introducing networked communication to MFGs, in particular to settings that use a single, non-episodic run of \(N\) decentralised agents to simulate the infinite population, as is likely to be most reasonable in real-world deployments. We prove that our architecture's sample guarantees lie between those of earlier theoretical algorithms for the centralised- and independent-learning architectures, varying dependent on network structure and the number of communication rounds. However, the sample guarantees of the three theoretical algorithms do not actually res

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybenjamin2023networked

Related papers

• Networked Communication For Mean-field Games With Function Approximation And Empirical Mean-field Estimation (2024)0.00
• Decentralized Mean Field Games (2021)3.58
• A Single Online Agent Can Efficiently Learn Mean Field Games (2024)0.00
• Generalization In Mean Field Games By Learning Master Policies (2021)7.81
• Mean Field Multi-agent Reinforcement Learning (2018)2.26
• On The Convergence Of Model Free Learning In Mean Field Games (2019)0.00
• Efficient And Scalable Deep Reinforcement Learning For Mean Field Control Games (2024)0.00
• A General Framework For Learning Mean-field Games (2020)0.00