On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)

Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
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
more &raquo; ... zes how a smaller state representation increases the asymptotic bias while decreasing the risk of overfitting.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/695">doi:10.24963/ijcai.2020/695</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/0001Z20.html">dblp:conf/ijcai/0001Z20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yx2wihhuobgmjjh4aevkbr33g4">fatcat:yx2wihhuobgmjjh4aevkbr33g4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104182154/https://www.ijcai.org/Proceedings/2020/0695.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/22/24/22242cd0805f6771c4620d28e467047eb5856d9f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/695"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>