Cooperative Matrix Game
收藏arXiv2025-09-30 收录
下载链接：
https://github.com/uoe-agents/matrix-games
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是一个非单调合作案例，其中两个协作的智能体必须寻找最优的纳什均衡。该数据集被用于评估QLLM算法的性能，所属任务是多智能体强化学习。
This dataset is a non-monotonic cooperative scenario where two collaborative AI Agents must seek the optimal Nash equilibrium. It is utilized to evaluate the performance of the QLLM algorithm, and its associated task is multi-agent reinforcement learning.
提供机构：
University of Edinburgh Agents
