{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:55:33Z","timestamp":1787025333045,"version":"build-2736575974"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p>We consider the problem of off-policy policy selection in reinforcement learning: using historical data generated from running one policy to compare two or more policies. We show that approaches based on importance sampling can be unfair---they can select the worse of two policies more often than not. We then give an example that shows importance sampling is systematically unfair in a practically relevant setting; namely, we show that it unreasonably favors shorter trajectory lengths. We then present sufficient conditions to theoretically guarantee fairness. Finally, we provide a practical importance sampling-based estimator to help mitigate the unfairness due to varying trajectory lengths.<\/jats:p>","DOI":"10.24963\/ijcai.2018\/729","type":"proceedings-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:49:10Z","timestamp":1530755350000},"page":"5239-5243","source":"Crossref","is-referenced-by-count":10,"title":["Importance Sampling for Fair Policy Selection"],"prefix":"10.24963","author":[{"given":"Shayan","family":"Doroudi","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"},{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S.","family":"Thomas","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Brunskill","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}","theme":"Artificial Intelligence","location":"Stockholm, Sweden","acronym":"IJCAI-2018","number":"27","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2018,7,13]]},"end":{"date-parts":[[2018,7,19]]}},"container-title":["Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:55:35Z","timestamp":1530755735000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2018\/729"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2018\/729","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}