{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:17:14Z","timestamp":1758673034923,"version":"3.44.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686110","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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":[[2025,9,22]]},"abstract":"<jats:p>Artificial Intelligence (AI) has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Introducing causality awareness into AI has the potential to enhance its performance by enabling a deeper understanding of the underlying mechanisms of the environment. In this working paper, we explore how an Agent can autonomously learn the causal structure of its environment through repeated interventions. Using a Python implementation, we simulate an Agent interacting with a world governed by a causal Directed Acyclic Graph (DAG), which dictates the system\u2019s dynamics but remains hidden from the Agent. The Agent\u2019s task is to accurately infer the causal DAG, even in the presence of noise and constraints such as limited intervention opportunities. To achieve this, the Agent performs interventions and applies linear regression to identify causal relationships, leveraging causal inference techniques to analyze the statistical significance of observed changes. We evaluate the performance of the causal discovery algorithm under both ideal and imperfect conditions, examining scenarios with constrained intervention budgets. Additionally, we propose strategies for efficiently discovering causal relationships in both unconstrained and resource-limited environments.<\/jats:p>","DOI":"10.3233\/faia250686","type":"book-chapter","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T14:38:41Z","timestamp":1758638321000},"source":"Crossref","is-referenced-by-count":0,"title":["Agent Meets World: Learning Causality Through Repeated Autonomous Interventions"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1343-4106","authenticated-orcid":false,"given":"Matteo","family":"Gregorini","sequence":"first","affiliation":[{"name":"University of Pisa, Italy"},{"name":"IIT-CNR, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5080-8110","authenticated-orcid":false,"given":"Chiara","family":"Boldrini","sequence":"additional","affiliation":[{"name":"IIT-CNR, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5574-7847","authenticated-orcid":false,"given":"Lorenzo","family":"Valerio","sequence":"additional","affiliation":[{"name":"IIT-CNR, Italy"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","HHAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T14:38:42Z","timestamp":1758638322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"ISBN":["9781643686110"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250686","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}