Grasper: A generalist pursuer for pursuit-evasion problems

P Li, S Li, X Wang, J Cerny, Y Zhang, S McAleer… - arxiv preprint arxiv …, 2024 - arxiv.org
Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an
evader in graph-based environments such as urban street networks. Recent advancements …

Learning decentralized partially observable mean field control for artificial collective behavior

K Cui, S Hauck, C Fabian, H Koeppl - arxiv preprint arxiv:2307.06175, 2023 - arxiv.org
Recent reinforcement learning (RL) methods have achieved success in various domains.
However, multi-agent RL (MARL) remains a challenge in terms of decentralization, partial …

Scalable, generalizable, and offline methods for imperfect-information extensive-form games

S Li - 2025 - dr.ntu.edu.sg
Imperfect-information extensive-form games (IIEFGs) offer a versatile framework for
modeling interactions between multiple players in stochastic and imperfect-information …

Hypernetwork-based approach for optimal composition design in partially controlled multi-agent systems

K Park, DM Concha, HR Lee, CG Lee, T Lee - arxiv preprint arxiv …, 2025 - arxiv.org
Partially Controlled Multi-Agent Systems (PCMAS) are comprised of controllable agents,
managed by a system designer, and uncontrollable agents, operating autonomously. This …

[HTML][HTML] Large-Scale Multi-Agent Reinforcement Learning via Mean Field Games

K Cui - 2024 - tuprints.ulb.tu-darmstadt.de
In this dissertation, we discuss the mathematically rigorous multi-agent reinforcement
learning frameworks of mean field games (MFG) and mean field control (MFC). Dynamical …

Partially Observable Multi-Agent Reinforcement Learning using Mean Field Control

K Cui, SH Hauck, C Fabian, H Koeppl - ICML 2024 Workshop: Aligning … - openreview.net
Recent reinforcement learning (RL) methods have achieved success in various domains.
However, multi-agent RL (MARL) remains a challenge in terms of decentralization, partial …