A Maximum Principle approach to deterministic Mean Field Games of Control with Absorption

2021-04-13 · Paulwin Graewe, Ulrich Horst, Ronnie Sircar

We study a class of deterministic mean field games on finite and infinite time horizons arising in models of optimal exploitation of exhaustible resources. The main characteristic of our game is an absorption constraint on the players' state process. As a result of the state constraint the optimal time of absorption becomes part of the equilibrium. This requires a novel approach when applying Pontyagin's maximum principle. We prove the existence and uniqueness of equilibria and solve the infinite horizon models in closed form. As players may drop out of the game over time, equilibrium production rates need not be monotone nor smooth.

📄 PDF Abstract BibTeX arXiv:2104.06152

Code (0)

등록된 구현이 없습니다.

Mean Field Portfolio Games with Epstein-Zin Preferences

2025-05-12 · Guanxing Fu, Ulrich Horst

We study mean field portfolio games under Epstein-Zin preferences, which naturally encompass the classical time-additive power utility as a special case. In a general non-Markovian framework, we establish a uniqueness re…

Maximum Causal Entropy Inverse Reinforcement Learning for Mean-Field Games

2024-01-12 · Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi

In this paper, we introduce the maximum casual entropy Inverse Reinforcement Learning (IRL) problem for discrete-time mean-field games (MFGs) under an infinite-horizon discounted-reward optimality criterion. The state sp…

reinforcement-learning Reinforcement Learning

Large Deviations Principle for Discrete-time Mean-field Games

2021-02-15 · Naci Saldi

In this paper, we establish a large deviations principle (LDP) for interacting particle systems that arise from state and action dynamics of discrete-time mean-field games under the equilibrium policy of the infinite-pop…

Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games with Average Reward

2026-06-15 · Şevket Kaan Alkır, Naci Saldı, Berkay Anahtarcı, Can Deha Karıksız arxiv

We study inverse reinforcement learning for discrete-time, infinite-horizon mean-field games (MFGs) under an average-reward criterion. Expert demonstrations are assumed to arise from a stationary mean-field equilibrium u…

Reinforcement Learning

Theoretical understanding of adversarial reinforcement learning via mean-field optimal control

2021-09-29 · ZiMing Wang, Fengxiang He, Tao Cui, DaCheng Tao

Adversarial reinforcement learning has been shown promising in solving games in adversarial environments, while the theoretical understanding is still premature. This paper theoretically analyses the convergence and gene…

Generalization Bounds reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)