带承诺的微分 Stackelberg 均衡的非耦合学习
Uncoupled Learning of Differential Stackelberg Equilibria with Commitments
AI总结：
针对去中心化多智能体合作中无法获知他人收益函数的问题，提出基于零阶梯度估计的非耦合学习动态，并证明其在相同条件下收敛到微分 Stackelberg 均衡，同时给出角色协商机制。
摘要：
在需要高度合作的多智能体问题中，成功往往取决于智能体相互适应彼此行为的能力。在此类设定中，一个自然的解概念是 Stackelberg 均衡，其中“领导者”智能体在“跟随者”智能体将针对该策略选择其最佳响应的前提下，选择使其自身收益最大化的策略。近期工作以“微分”Stackelberg 均衡的形式，将这一解概念扩展到双人可微博弈，例如由多智能体深度强化学习产生的博弈。尽管先前工作提出了收敛到此类均衡的学习动态，但这些动态是“耦合的”，即领导者策略的学习更新需要关于跟随者收益函数的某些信息。因此，这些方法无法应用于真正去中心化的多智能体设定，尤其是临时合作，其中每个智能体只能访问自己的收益函数。在本文中，我们提出基于零阶梯度估计器的“非耦合”学习动态，其中每个智能体的策略更新仅依赖于其对另一方行为的观察。我们分析了这些动态在一般和博弈中的收敛性，并证明它们在与先前耦合方法相同的条件下收敛到微分 Stackelberg 均衡。此外，我们提出了一种在线机制，对称学习者可通过它协商领导者—跟随者角色。最后，我们讨论了本工作对多智能体强化学习以及更广泛的临时协作的意义。
英文摘要：
In multi-agent problems requiring a high degree of cooperation, success often depends on the ability of the agents to adapt to each other's behavior. A natural solution concept in such settings is the Stackelberg equilibrium, in which the ``leader'' agent selects the strategy that maximizes its own payoff given that the ``follower'' agent will choose their best response to this strategy. Recent work has extended this solution concept to two-player differentiable games, such as those arising from multi-agent deep reinforcement learning, in the form of the \textit{differential} Stackelberg equilibrium. While this previous work has presented learning dynamics which converge to such equilibria, these dynamics are ``coupled'' in the sense that the learning updates for the leader's strategy require some information about the follower's payoff function. As such, these methods cannot be applied to truly decentralised multi-agent settings, particularly ad hoc cooperation, where each agent only has access to its own payoff function. In this work we present ``uncoupled'' learning dynamics based on zeroth-order gradient estimators, in which each agent's strategy update depends only on their observations of the other's behavior. We analyze the convergence of these dynamics in general-sum games, and prove that they converge to differential Stackelberg equilibria under the same conditions as previous coupled methods. Furthermore, we present an online mechanism by which symmetric learners can negotiate leader-follower roles. We conclude with a discussion of the implications of our work for multi-agent reinforcement learning and ad hoc collaboration more generally.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
