Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs

Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents' contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-06
Hauptverfasser: Triantafyllou, Stelios, Sukovic, Aleksa, Mandal, Debmalya, Radanovic, Goran
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Triantafyllou, Stelios
Sukovic, Aleksa
Mandal, Debmalya
Radanovic, Goran
description Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents' contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent's action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents' actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent's action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2878531597</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2878531597</sourcerecordid><originalsourceid>FETCH-proquest_journals_28785315973</originalsourceid><addsrcrecordid>eNqNjEELgjAYQEcQJOV_-KDzwLaW1k3M6CIIdZchm0zGZn7boX9fhD-g04PH461Iwjg_0OLI2IakiGOWZeyUMyF4QtpyUC7Qx6R6o00PtdaqD3iBEioZUdrFQDv7SQ4yGO-gdNK-0SAYB020wdDfBZprizuy1tKiShduyf5WP6s7nWb_igpDN_o4fwfYsSIvBD-Ic87_qz6m7T2g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2878531597</pqid></control><display><type>article</type><title>Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs</title><source>Free E- Journals</source><creator>Triantafyllou, Stelios ; Sukovic, Aleksa ; Mandal, Debmalya ; Radanovic, Goran</creator><creatorcontrib>Triantafyllou, Stelios ; Sukovic, Aleksa ; Mandal, Debmalya ; Radanovic, Goran</creatorcontrib><description>Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents' contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent's action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents' actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent's action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Decision making ; Markov processes ; Multiagent systems</subject><ispartof>arXiv.org, 2024-06</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Triantafyllou, Stelios</creatorcontrib><creatorcontrib>Sukovic, Aleksa</creatorcontrib><creatorcontrib>Mandal, Debmalya</creatorcontrib><creatorcontrib>Radanovic, Goran</creatorcontrib><title>Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs</title><title>arXiv.org</title><description>Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents' contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent's action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents' actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent's action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.</description><subject>Algorithms</subject><subject>Decision making</subject><subject>Markov processes</subject><subject>Multiagent systems</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjEELgjAYQEcQJOV_-KDzwLaW1k3M6CIIdZchm0zGZn7boX9fhD-g04PH461Iwjg_0OLI2IakiGOWZeyUMyF4QtpyUC7Qx6R6o00PtdaqD3iBEioZUdrFQDv7SQ4yGO-gdNK-0SAYB020wdDfBZprizuy1tKiShduyf5WP6s7nWb_igpDN_o4fwfYsSIvBD-Ic87_qz6m7T2g</recordid><startdate>20240610</startdate><enddate>20240610</enddate><creator>Triantafyllou, Stelios</creator><creator>Sukovic, Aleksa</creator><creator>Mandal, Debmalya</creator><creator>Radanovic, Goran</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240610</creationdate><title>Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs</title><author>Triantafyllou, Stelios ; Sukovic, Aleksa ; Mandal, Debmalya ; Radanovic, Goran</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28785315973</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Decision making</topic><topic>Markov processes</topic><topic>Multiagent systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Triantafyllou, Stelios</creatorcontrib><creatorcontrib>Sukovic, Aleksa</creatorcontrib><creatorcontrib>Mandal, Debmalya</creatorcontrib><creatorcontrib>Radanovic, Goran</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Triantafyllou, Stelios</au><au>Sukovic, Aleksa</au><au>Mandal, Debmalya</au><au>Radanovic, Goran</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs</atitle><jtitle>arXiv.org</jtitle><date>2024-06-10</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents' contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent's action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents' actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent's action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_2878531597
source Free E- Journals
subjects Algorithms
Decision making
Markov processes
Multiagent systems
title Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T16%3A51%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Agent-Specific%20Effects:%20A%20Causal%20Effect%20Propagation%20Analysis%20in%20Multi-Agent%20MDPs&rft.jtitle=arXiv.org&rft.au=Triantafyllou,%20Stelios&rft.date=2024-06-10&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2878531597%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2878531597&rft_id=info:pmid/&rfr_iscdi=true