Stubborn: 一种用于评估具有相似激励的代理之间顽固性的环境（英文版）

英文标题：Stubborn: An Environment for Evaluating Stubbornness between Agents with Aligned Incentives中文摘要：本文主要介绍了一种基于多智能体强化学习 (MARL) 的环境 Stubborn，用于研究完全合作环境下代理之间的固执程度对社会动态的影响，并探究如何通过这种固执行为来提高环境中代理的智能行为选择。英文摘要：Recent research in multi-agent reinforcement learning (MARL) has shownsuccess in learning social behavior and cooperation. Social dilemmas betweenagents in mixed-sum settings have been studied extensively, but there is littleresearch into social dilemmas in fullycooperative settings, where agen