Reinforcement Learning For Mean Field Games With Strategic Complementarities

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylee2020reinforcement

Related papers

• A General Framework For Learning Mean-field Games (2020)0.00
• Learning In Mean Field Games: A Survey (2022)0.00
• A Single Online Agent Can Efficiently Learn Mean Field Games (2024)0.00
• Approximately Solving Mean Field Games Via Entropy-regularized Deep Reinforcement Learning (2021)0.00
• Oracle-free Reinforcement Learning In Mean-field Games Along A Single Sample Path (2022)0.00
• Unified Reinforcement Q-learning For Mean Field Game And Control Problems (2020)0.00
• Efficient And Scalable Deep Reinforcement Learning For Mean Field Control Games (2024)0.00
• On The Convergence Of Model Free Learning In Mean Field Games (2019)0.00