PulseAugur
中
实时 04:01:33
English(EN) Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning

新研究将累积前景理论整合到多智能体老虎机问题中

作者 PulseAugur 编辑部 · [2 个来源] ·

本文在竞争性双边匹配市场中，针对多智能体多臂老虎机问题提出了一种新颖的方法。它结合了累积前景理论（CPT）来模拟人类偏好，该理论对智能体行为进行非线性加权。该研究分析了CPT扭曲奖励下的现有学习算法，推导出了玩家最优的遗憾界限。进一步提出了改进措施，以增强遗憾保证，特别是在臂的数量远超玩家数量的情况下。该研究还解决了对抗性市场条件，开发了CPT作为风险敏感度度量的鲁棒市场算法，并建立了对数遗憾保证。 AI

影响 为竞争性AI环境中的决策引入了新颖的理论框架。

排序理由 该集群包含一篇发表在arXiv上的学术论文。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新研究将累积前景理论整合到多智能体老虎机问题中

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇发表在arXiv上的学术论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
133 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Ananya Kunisetty, Avishek Ghosh ·

    匹配市场与累积前景理论：迈向最优和对抗性鲁棒学习

    arXiv:2606.19883v1 Announce Type: cross Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model. To capture human preferences, we use cumulative prospect theory (CPT) that wei…

  2. arXiv stat.ML TIER_1 English(EN) · Avishek Ghosh ·

    匹配市场与累积前景理论：迈向最优和对抗性鲁棒学习

    We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model. To capture human preferences, we use cumulative prospect theory (CPT) that weighs the actions of the agent in a nonlinear fashio…

相关实体

相关话题