Observation Interference in Partially Observable Assistance Games

Scott Emmons; Caspar Oesterheld; Vincent Conitzer; Stuart Russell

ICML2025顶会

Observation Interference in Partially Observable Assistance Games

Scott Emmons, Caspar Oesterheld, Vincent Conitzer, Stuart Russell

出版方

2025年份

1顶会引用

摘要

We study partially observable assistance games (POAGs), a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. Motivated

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。

核心论断
谁在沿用
横向对比
局限

你的问题

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始，无需绑卡

引用它的顶会 Paper1

More Capable, Less Cooperative? When LLMs Fail at Zero-Cost CollaborationAdvait Yadav, Sidney Black, Oliver SourbutICML 2026 · 被引用 2 次

问问它们各自怎么用它

它引用的顶会 Paper6

"Other-Play" for Zero-Shot CoordinationHengyuan Hu, Adam Lerer, Alex Peysakhovich, Jakob N. FoersterICML 2020 · 被引用 271 次
Honesty Is the Best Policy: Defining and Mitigating AI DeceptionFrancis Ward, Francesca Toni, Francesco Belardinelli, Tom EverittNeurIPS 2023 · 被引用 60 次
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human ModelsCassidy Laidlaw, Anca D. DraganICLR 2022 · 被引用 46 次
A New Formalism, Method and Open Issues for Zero-Shot CoordinationJohannes Treutlein, Michael Dennis, Caspar Oesterheld, Jakob N. FoersterICML 2021 · 被引用 45 次
Learning to Interactively Learn and AssistMark Woodward, Chelsea Finn, Karol HausmanAAAI 2020 · 被引用 37 次

摘要

问问这篇 Paper

智能体会读完全文。

引用它的顶会 Paper1

它引用的顶会 Paper6

相关 Paper