Reinforcement Learning for Mean Field Games with Strategic Complementarities

2020-06-21 · Kiyeob Lee, Desik Rengarajan, Dileep Kalathil, Srinivas Shakkottai

Mean Field Games (MFG) are the class of games with a very large number of agents and the standard equilibrium concept is a Mean Field Equilibrium (MFE). Algorithms for learning MFE in dynamic MFGs are unknown in general. Our focus is on an important subclass that possess a monotonicity property called Strategic Complementarities (MFG-SC). We introduce a natural refinement to the equilibrium concept that we call Trembling-Hand-Perfect MFE (T-MFE), which allows agents to employ a measure of randomization while accounting for the impact of such randomization on their payoffs. We propose a simple algorithm for computing T-MFE under a known model. We also introduce a model-free and a model-based approach to learning T-MFE and provide sample complexities of both algorithms. We also develop a fully online learning scheme that obviates the need for a simulator. Finally, we empirically evaluate the performance of the proposed algorithms via examples motivated by real-world applications.

📄 PDF Abstract BibTeX arXiv:2006.11683

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Nash equilibria of games with generalized complementarities

2024-06-30 · Lu Yu

To generalize complementarities for games, we introduce some conditions weaker than quasisupermodularity and the single crossing property. We prove that the Nash equilibria of a game satisfying these conditions form a no…

Weak Monotone Comparative Statics

2019-11-15 · Yeon-Koo Che, Jinwoo Kim, Fuhito Kojima

We develop a theory of monotone comparative statics based on weak set order -- in short, weak monotone comparative statics -- and identify the enabling conditions in the context of individual choices, Pareto optimal choi…

Games Under Network Uncertainty

2023-05-04 · Promit K. Chaudhuri, Matthew O. Jackson, Sudipta Sarangi, Hector Tzavellas

We examine settings in which agents choose behaviors and care about their neighbors' behaviors, but have incomplete information about the network in which they are embedded. We develop a model in which agents use local k…

Scalable Deep Reinforcement Learning Algorithms for Mean Field Games

2022-03-22 · Mathieu Laurière, Sarah Perrin, Sertan Girgin, Paul Muller 외

Mean Field Games (MFGs) have been introduced to efficiently approximate games with very large populations of strategic agents. Recently, the question of learning equilibria in MFGs has gained momentum, particularly using…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL

2024-02-08 · Jiawei Huang, Niao He, Andreas Krause

We study the sample complexity of reinforcement learning (RL) in Mean-Field Games (MFGs) with model-based function approximation that requires strategic exploration to find a Nash Equilibrium policy. We introduce the Par…

Computational Efficiency Reinforcement Learning (RL)