V
主页
京东 11.11 红包
2022微软亚洲研究院数据驱动的优化方法研讨会 报告三：Inverse Game Theory for Stackelberg Games
发布人
Speaker: Weiran Shen Affiliation: Renmin University of China Title: Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality Abstract: Optimizing strategic decisions (a.k.a. computing equilibrium) is key to the success of many non-cooperative multi-agent applications. However, in many real-world situations, we may face the exact opposite of this game-theoretic problem — instead of prescribing equilibrium of a given game, we may directly observe the agents’ equilibrium behaviors but want to infer the underlying parameters of an unknown game. This research question, also known as inverse game theory, has been studied in multiple recent works in the context of Stackelberg games. Unfortunately, existing works exhibit quite negative results, showing statistical hardness and computational hardness, assuming follower’s perfectly rational behaviors. Our work relaxes the perfect rationality agent assumption to the classic quantal response model, a more realistic behavior model of bounded rationality. Interestingly, we show that the smooth property brought by such bounded rationality model actually leads to provably more efficient learning of the follower utility parameters in general Stackelberg games. Systematic empirical experiments on synthesized games confirm our theoretical results and further suggest its robustness beyond the strict quantal response model.
打开封面
下载高清视频
观看高清视频
视频下载器
微软亚洲研究院理论中心前沿系列讲座 第一期 Unveiling Transformers With LEGO
智见她未来—微软女性数字创新机遇论坛 2022（上集）
微软亚洲研究院理论中心前沿系列讲座 第五期 What Should a Good Deep Neural Network Look Like?
【Research Forum】人工智能时代的研究
微软亚洲研究院理论中心前沿系列讲座 第三期 Local Elasticity of NN and Its Inspired Theory
微软亚洲研究院理论中心前沿系列讲座 第十期 Understanding Adam and AdamW
2022微软亚洲研究院数据驱动的优化方法研讨会 报告十一：Oblivious Online Contention Resolution Schemes
从技术革命到文化创新：云计算在这里孕育新火花
2022微软亚洲研究院数据驱动的优化方法研讨会 报告十二：Online Facility Location with Predictions
Ada Workshop 2022 主题演讲：龚文君
当亚马逊雨林会说话，你会听到什么？
(超爽中英!) 2024公认最好的【Agent智能体】系列教程！带你从0到1构建自己的智能体！
生成式AI工具MatterGen ：定制生成稳定新型材料
【Research Forum】利用 AI 增强人类认知和决策能力
老牌产业大国，如何用云和AI技术重焕生机？
Do More With Less! 与科技圈的无界对话
2018微软技术暨生态大会10月26日直播录播p2
微软Inspire 2023 大会全程回顾 中文字幕版
开发云原生应用—第五课
是什么塑造了公司的创新文化?
开发云原生应用—第三课
让AI无缝融入生产力！ Dynamics 365 & Power Platform上新
【Azure Friday】Microsoft Azure 混合连接概述
【ICLR 2023论文分享】T-GNNExplainer：时序图上的解释器
【Azure Friday】为您的混合环境选择合适的数据解决方案
Tightly Connecting Vision and Language
机器学习基础和基础模型研讨会-Contrastive Learning Is Spectral Clustering On Similarity Graph
A Truly Unbiased Model
2020 Spring Unithon Roadshow
2023机器学习基础和基础模型研讨会-Analysis of a toy case for emergence
Zero-Shot Detection via Vision and Language Knowledge Distillation
【Azure Friday】Azure Kubernetes 服务的 Teleport 功能概述
“计算之美”之 Ada Workshop 2021 | 王莹《漫画式科研梦想：做开源世界的“神奇女侠”》
我的电脑里也有「商业机密」？Copilot提供全方位保护
开源系列讲座 | 微软人工智能教育与学习共建社区全新更新，更有精品课程首度公开！
温和的走进深度学习（下）
#AI无界 因你声动#特别活动完整回放
【Azure Friday】Azure Blob 存储数据保护功能
【资讯】更新安卓yuzu/sudachi固件19.0.1
2018微软技术暨生态大会直播回顾P2
