Decentralized Mean Field Games

Abstract

Multiagent reinforcement learning algorithms have not been widely adopted in large scale environments with many agents as they often scale poorly with the number of agents. Using mean field theory to aggregate agents has been proposed as a solution to this problem. However, almost all previous methods in this area make a strong assumption of a centralized system where all the agents in the environment learn the same policy and are effectively indistinguishable from each other. In this paper, we relax this assumption about indistinguishable agents and propose a new mean field system known as Decentralized Mean Field Games, where each agent can be quite different from others. All agents learn independent policies in a decentralized fashion, based on their local observations. We define a theoretical solution concept for this system and provide a fixed point guarantee for a Q-learning based algorithm in this system. A practical consequence of our approach is that we can address a `chicken-

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keysubramanian2021decentralized

Related papers

• Mean Field Multi-agent Reinforcement Learning (2018)2.26
• Networked Communication For Decentralised Agents In Mean-field Games (2023)0.00
• Multi Type Mean Field Reinforcement Learning (2020)0.00
• Partially Observable Mean Field Reinforcement Learning (2020)0.00
• A Single Online Agent Can Efficiently Learn Mean Field Games (2024)0.00
• On The Convergence Of Model Free Learning In Mean Field Games (2019)0.00
• Robust Cooperative Multi-agent Reinforcement Learning:a Mean-field Type Game Perspective (2024)0.00
• Efficient And Scalable Deep Reinforcement Learning For Mean Field Control Games (2024)0.00