Inference-Based Strategy Alignment for General-Sum Differential Games
Inference-Based Strategy Alignment for General-Sum Differential Games
复制标题
广义和微分博弈的基于推理的策略调整
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Zachary Sunberg
中科院分区：
文献类型：
--
作者：
Lasse Peters;David Fridovich;C. Tomlin;Zachary Sunberg
在多个代理交互的许多设置中，每个代理的最佳选择在很大程度上取决于其他代理的选择。这些耦合的相互作用可以通过一般和微分博弈来很好地描述，其中参与者具有不同的目标，状态在连续时间内演变，并且最佳游戏可以由许多均衡概念之一来表征，例如，纳什均衡通常情况下，问题都存在多重均衡。从这样一个博弈中的单个代理人的角度来看，这种解决方案的多样性可能会引入其他代理人将如何表现的不确定性。本文提出了一个一般框架，解决均衡之间的歧义推理的均衡其他代理人的目标。我们在模拟多玩家人机导航问题中展示了这个框架，得出了两个主要结论：第一，通过推断人类在哪种平衡状态下操作，机器人能够更准确地预测轨迹，第二，通过发现并调整自己到这种平衡状态，机器人能够降低所有玩家的成本。
In many settings where multiple agents interact, the optimal choices for each agent depend heavily on the choices of the others. These coupled interactions are well-described by a general-sum differential game, in which players have differing objectives, the state evolves in continuous time, and optimal play may be characterized by one of many equilibrium concepts, e.g., a Nash equilibrium. Often, problems admit multiple equilibria. From the perspective of a single agent in such a game, this multiplicity of solutions can introduce uncertainty about how other agents will behave. This paper proposes a general framework for resolving ambiguity between equilibria by reasoning about the equilibrium other agents are aiming for. We demonstrate this framework in simulations of a multi-player human-robot navigation problem that yields two main conclusions: First, by inferring which equilibrium humans are operating at, the robot is able to predict trajectories more accurately, and second, by discovering and aligning itself to this equilibrium the robot is able to reduce the cost for all players.