分散部分可观察mdp中计算效率的责任归属

Stelios Triantafyllou, Goran Radanovic
{"title":"分散部分可观察mdp中计算效率的责任归属","authors":"Stelios Triantafyllou, Goran Radanovic","doi":"10.48550/arXiv.2302.12676","DOIUrl":null,"url":null,"abstract":"Responsibility attribution is a key concept of accountable multi-agent decision making. Given a sequence of actions, responsibility attribution mechanisms quantify the impact of each participating agent to the final outcome. One such popular mechanism is based on actual causality, and it assigns (causal) responsibility based on the actions that were found to be pivotal for the considered outcome. However, the inherent problem of pinpointing actual causes and consequently determining the exact responsibility assignment has shown to be computationally intractable. In this paper, we aim to provide a practical algorithmic solution to the problem of responsibility attribution under a computational budget. We first formalize the problem in the framework of Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) augmented by a specific class of Structural Causal Models (SCMs). Under this framework, we introduce a Monte Carlo Tree Search (MCTS) type of method which efficiently approximates the agents' degrees of responsibility. This method utilizes the structure of a novel search tree and a pruning technique, both tailored to the problem of responsibility attribution. Other novel components of our method are (a) a child selection policy based on linear scalarization and (b) a backpropagation procedure that accounts for a minimality condition that is typically used to define actual causality. We experimentally evaluate the efficacy of our algorithm through a simulation-based test-bed, which includes three team-based card games.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs\",\"authors\":\"Stelios Triantafyllou, Goran Radanovic\",\"doi\":\"10.48550/arXiv.2302.12676\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Responsibility attribution is a key concept of accountable multi-agent decision making. Given a sequence of actions, responsibility attribution mechanisms quantify the impact of each participating agent to the final outcome. One such popular mechanism is based on actual causality, and it assigns (causal) responsibility based on the actions that were found to be pivotal for the considered outcome. However, the inherent problem of pinpointing actual causes and consequently determining the exact responsibility assignment has shown to be computationally intractable. In this paper, we aim to provide a practical algorithmic solution to the problem of responsibility attribution under a computational budget. We first formalize the problem in the framework of Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) augmented by a specific class of Structural Causal Models (SCMs). Under this framework, we introduce a Monte Carlo Tree Search (MCTS) type of method which efficiently approximates the agents' degrees of responsibility. This method utilizes the structure of a novel search tree and a pruning technique, both tailored to the problem of responsibility attribution. Other novel components of our method are (a) a child selection policy based on linear scalarization and (b) a backpropagation procedure that accounts for a minimality condition that is typically used to define actual causality. We experimentally evaluate the efficacy of our algorithm through a simulation-based test-bed, which includes three team-based card games.\",\"PeriodicalId\":326727,\"journal\":{\"name\":\"Adaptive Agents and Multi-Agent Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-02-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Adaptive Agents and Multi-Agent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2302.12676\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adaptive Agents and Multi-Agent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2302.12676","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

责任归因是多主体问责决策的一个重要概念。给定一系列行动,责任归因机制量化每个参与主体对最终结果的影响。其中一种流行的机制是基于实际的因果关系,它根据被发现对所考虑的结果至关重要的行为来分配(因果)责任。然而,确定实际原因并因此确定确切责任分配的固有问题在计算上是难以解决的。在本文中,我们的目标是提供一个实用的算法解决在计算预算下的责任归属问题。我们首先在分散部分可观察马尔可夫决策过程(deco - pomdp)的框架中形式化了这个问题,该决策过程由一类特定的结构因果模型(scm)扩充。在此框架下,我们引入了一种蒙特卡罗树搜索(MCTS)类型的方法,该方法有效地逼近了智能体的责任程度。该方法利用了一种新的搜索树结构和修剪技术,这两种技术都是针对责任归属问题量身定制的。我们方法的其他新颖组成部分是(a)基于线性标量化的子选择策略和(b)考虑最小条件的反向传播过程,该最小条件通常用于定义实际因果关系。我们通过一个基于模拟的测试平台实验评估了我们算法的有效性,其中包括三个基于团队的纸牌游戏。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs
Responsibility attribution is a key concept of accountable multi-agent decision making. Given a sequence of actions, responsibility attribution mechanisms quantify the impact of each participating agent to the final outcome. One such popular mechanism is based on actual causality, and it assigns (causal) responsibility based on the actions that were found to be pivotal for the considered outcome. However, the inherent problem of pinpointing actual causes and consequently determining the exact responsibility assignment has shown to be computationally intractable. In this paper, we aim to provide a practical algorithmic solution to the problem of responsibility attribution under a computational budget. We first formalize the problem in the framework of Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) augmented by a specific class of Structural Causal Models (SCMs). Under this framework, we introduce a Monte Carlo Tree Search (MCTS) type of method which efficiently approximates the agents' degrees of responsibility. This method utilizes the structure of a novel search tree and a pruning technique, both tailored to the problem of responsibility attribution. Other novel components of our method are (a) a child selection policy based on linear scalarization and (b) a backpropagation procedure that accounts for a minimality condition that is typically used to define actual causality. We experimentally evaluate the efficacy of our algorithm through a simulation-based test-bed, which includes three team-based card games.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信