{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:39:37Z","timestamp":1723016377865},"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":[[2020,7]]},"abstract":"<jats:p>When an agent has limited information on its environment, the suboptimality of an RL algorithm can be decomposed into the sum of two terms: a term related to an asymptotic bias (suboptimality with unlimited data) and a term due to overfitting (additional suboptimality due to limited data). In the context of reinforcement learning with partial observability, this paper provides an analysis of the tradeoff between these two error sources. In particular, our theoretical analysis formally characterizes how a smaller state representation increases the asymptotic bias while decreasing the risk of overfitting.<\/jats:p>","DOI":"10.24963\/ijcai.2020\/706","type":"proceedings-article","created":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T12:12:10Z","timestamp":1594210330000},"page":"5055-5059","source":"Crossref","is-referenced-by-count":1,"title":["On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)"],"prefix":"10.24963","author":[{"given":"Vincent","family":"Francois-Lavet","sequence":"first","affiliation":[{"name":"McGill University"},{"name":"Mila"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillaume","family":"Rabusseau","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Montr\u00e9al"},{"name":"Mila"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joelle","family":"Pineau","sequence":"additional","affiliation":[{"name":"McGill University"},{"name":"Mila"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Li\u00e8ge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raphael","family":"Fonteneau","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Li\u00e8ge"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-PRICAI-2020","name":"Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}","start":{"date-parts":[[2020,7,11]]},"theme":"Artificial Intelligence","location":"Yokohama, Japan","end":{"date-parts":[[2020,7,17]]}},"container-title":["Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2020,7,9]],"date-time":"2020-07-09T02:16:47Z","timestamp":1594261007000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2020\/706"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2020\/706","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}