{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:35:54Z","timestamp":1761176154995,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>To reliably deploy Multi-Agent Reinforcement Learning (MARL) systems, it is crucial to understand individual agent behaviors. While prior work typically evaluates overall team performance based on explicit reward signals, it is unclear how to infer agent contributions in the absence of any value feedback. In this work, we investigate whether meaningful insights into agent behaviors can be extracted solely by analyzing the policy distribution. Inspired by the phenomenon that intelligent agents tend to pursue convergent instrumental values, we introduce Intended Cooperation Values (ICVs), a method based on information-theoretic Shapley values for quantifying each agent\u2019s causal influence on their co-players\u2019 instrumental empowerment. Specifically, ICVs measure an agent\u2019s action effect on its teammates\u2019 policies by assessing their decision (un)certainty and preference alignment. By analyzing action effects on policies and value functions across cooperative and competitive MARL tasks, our method identifies which agent behaviors are beneficial to team success, either by fostering deterministic decisions or by preserving flexibility for future action choices, while also revealing the extent to which agents adopt similar or diverse strategies. Our proposed method offers novel insights into cooperation dynamics and enhances explainability in MARL systems.<\/jats:p>","DOI":"10.3233\/faia250947","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:46:43Z","timestamp":1761126403000},"source":"Crossref","is-referenced-by-count":0,"title":["Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learning"],"prefix":"10.3233","author":[{"given":"Ardian","family":"Selmonaj","sequence":"first","affiliation":[{"name":"Istituto Dalle Molle di Studi sull\u2019Intelligenza Artificiale (IDSIA), USI-SUPSI, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miroslav","family":"\u0160trupl","sequence":"additional","affiliation":[{"name":"Istituto Dalle Molle di Studi sull\u2019Intelligenza Artificiale (IDSIA), USI-SUPSI, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oleg","family":"Szehr","sequence":"additional","affiliation":[{"name":"Istituto Dalle Molle di Studi sull\u2019Intelligenza Artificiale (IDSIA), USI-SUPSI, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Antonucci","sequence":"additional","affiliation":[{"name":"Istituto Dalle Molle di Studi sull\u2019Intelligenza Artificiale (IDSIA), USI-SUPSI, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:46:43Z","timestamp":1761126403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250947"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250947","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}