<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Volodymyr Tkachuk</style></author><author><style face="normal" font="default" size="100%">Sriram Ganapathi Subramanian</style></author><author><style face="normal" font="default" size="100%">Matthew E Taylor</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning</style></title><secondary-title><style face="normal" font="default" size="100%">International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2021), London, UK - Adaptive Learning Agents Workshop</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2021</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://arxiv.org/pdf/2103.04416.pdf</style></url></web-urls></urls><language><style face="normal" font="default" size="100%">eng</style></language></record></records></xml>