While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner's strategy and adapt our policy to that strategy, all without knowledge of the environment reward or dynamics. We formalize this problem of conditional multi-agent imitation learning, and propose a novel approach to address the difficulties of scalability and data scarcity. Our key insight is that variations across partners in multi-agent games are often highly structured, and can be represented via a low-rank subspace. Leveraging tools from tensor decomposition, our model learns a low-rank subspace over ego and partner agent strategies, then infers and adapts to a new partner strategy by interpolating in the subspace. We experiments with a mix of collaborative tasks, including bandits, particle, and Hanabi environments. Additionally, we test our conditional policies against real human partners in a user study on the Overcooked game. Our model adapts better to new partners compared to baselines, and robustly handles diverse settings ranging from discrete/continuous actions and static/online evaluation with AI/human partners.
翻译:虽然在多试剂学习方面的进步使培训日益复杂的代理人成为了培训日益复杂的代理人,但大多数现有技术都产生了最终政策,而这种政策并非旨在适应新的伙伴的战略。然而,我们希望我们的AI代理商根据周围伙伴的战略调整其战略。在这项工作中,我们研究有条件的多试剂模拟学习问题,在培训期间,我们有机会获得联合轨迹演示,我们必须与新的伙伴互动,并在测试时适应新的伙伴。这一环境具有挑战性,因为我们必须推导一个新的伙伴战略,使我们的政策适应于这一战略,完全没有环境奖赏或动态的知识。我们把有条件的多试剂模仿学习的问题正式化,并提议一种新颖的方法来解决可扩缩和数据匮乏的困难。我们的主要洞察力是,多试探性多试玩游戏伙伴之间的差异往往结构性很强,并且可以通过低层次的子空间来体现。我们模型从自我和伙伴的多样化战略中吸取了低层次的次空间,然后通过对新的伙伴战略进行调整和适应新的伙伴战略。我们在次空间的跨空间里学习这个新伙伴的学习,包括跨级的磁带实验,我们用一个合作的实验,我们对模型的模型的模型的模型的模型的模型的模型的模型,我们,我们用一个模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的混合,我们,我们比比比的模型的模型的模型,我们的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型的模型,我们,我们比比比比比。