[论文] Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc T...

论文概要

研究领域: ML
作者: Peter Tisnikar, Maja Swieczkowska, Benteng Ma, Gerard Canal, Matteo Leonetti
发布时间: 2026-07-29
arXiv: 2607.27177

中文摘要

与新颖多样的伙伴有效协作是自主智能体的关键技能。当前大多数临时团队协作（AHT）方法假设智能体将在单一固定任务上协作，且伙伴的能力（成功执行期望动作的能力）是已知的。现实中，伙伴的真实能力往往是隐藏的，人类协作者可能在有多个有效策略的任务上表现次优。为解决这些局限，我们将临时团队协作扩展到多任务设置，将其重构为在隐藏伙伴能力下的联合规划与分布式执行问题。我们提出CE-CM（通过上下文模型进行能力估计），一种近似贝叶斯方法，推断任务不变的能力向量。通过基于模拟的采样，智能体估计能力并诱导上下文多智能体马尔可夫决策过程进行规划。该方法无需群体预训练，仅通过少量任务在线精炼信念。为应对人类不可预测性，我们提出CE-CM-Div，一种扩展，针对多样化的规划器rollout而非单一最优轨迹评估能力假设。模拟实验表明CE-CM能快速恢复隐藏能力，减少不可行动作分配，并适应时变。此外，在来自15名参与者的225条轨迹的离线人类研究中，CE-CM-Div显著优于基线CE-M方法。我们的结果表明，基于能力的建模在所研究场景中是一种有前景的可解释、任务无关的表征，证明考虑行为多样性对于鲁棒的人机协作至关重要。

原文摘要

Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents. Most current ad-hoc teamwork (AHT) approaches assume that agents will collaborate on a single, fixed task and that the partner's capabilities, their ability to successfully execute the desired action, are already known. In reality, a partner's true capabilities are often hidden, and human collaborators may act sub-optimally on tasks with multiple valid strategies. To address these limitations, we extend ad-hoc teamwork into a multi-task setting by re-framing it as a problem of joint planning with decentralised execution under hidden partner capabilities. We introduce CE-CM (Capability Estimation via Contextual Models), an approximate Bayesian method that infers task-invariant capability vector...

自动采集于 2026-07-31

#论文 #arXiv #ML #小凯