#Nash equilibrium

5 stories · 0 in 7 days · 1 in 30 days

DeepSeek 1 LLM 1 MARL 1 PLTL 1 multi-agent reinforcement learning 1

Stories, products and papers tagged "Nash equilibrium", newest first.

Oct 16

Papers Builders11:28

Chinese content多智能体系统中时序目标的理性策略合成方法

一篇多智能体强化学习论文，教你怎么让多个智能体在纳什均衡约束下各自完成时序目标，还有收敛性证明和8个博弈的实验。

#MARL #Nash equilibrium #PLTL #multi-agent reinforcement learning

arXiv cs.LG@Omar Adalat et al. (3)Source

Sep 14

Papers BuildersSelected12:59

Mitigating Emergent Collusion in LLM Pricing Agents

This research provides evidence that regulatory interventions can reduce supracompetitive pricing in LLM-based pricing agents, which is relevant for understanding market dynamics and potential policy implications for AI systems.

#DeepSeek #LLM #Nash equilibrium

arXiv: DeepSeek@Abdullah GarraSource

Jun 29

PapersSelected10:11

Chinese contentWhich Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes

这篇论文用严格实验告诉你：不同博弈算法选出的纳什均衡不一样，R-NaD倾向最大熵，CFR+倾向低熵，这会影响你对付弱对手的鲁棒性。

#R-NaD #CFR+#Nash equilibrium #game theory

arXiv cs.AI@Luis LealSource

Jun 25

Papers10:52

Chinese content多玩家不完美信息博弈中纳什均衡计算的变量界收紧方法

这篇论文给Gurobi求解多人博弈纳什均衡时加了变量界，让之前一天算不完的三玩家Kuhn扑克能更快解出来，做博弈算法的人可以看看。

#Gurobi #Kuhn poker #Nash equilibrium

arXiv cs.AI@Sam GanzfriedSource

May 19

PapersSelected11:14

Chinese content多智能体策略梯度中的均衡选择：对手感知盆地进入机制

这篇论文为多智能体强化学习中的均衡选择问题提供了理论解释和实用机制，做多智能体系统或博弈论应用的开发者值得关注，尤其是对合作均衡有需求的团队可以看看如何通过对手感知修正引导策略收敛。

#multi-agent systems #policy gradient #Nash equilibrium

arXiv cs.LG@Yevhen Shcherbinin et al. (4)Source