Temporal difference learning with eligibility traces for the game connect four

Markus Thill, Samineh Bagheri, Patrick Koch, Wolfgang Konen
<span title="">2014</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rhd7ssklwncwpd7fotjzyiag4e" style="color: black;">2014 IEEE Conference on Computational Intelligence and Games</a> </i> &nbsp;
Systems that learn to play board games are often trained by self-play on the basis of temporal difference (TD) learning. Successful examples include Tesauro's well known TD-Gammon and Lucas' Othello agent. For other board games of moderate complexity like Connect Four, we found in previous work that a successful system requires a very rich initial feature set with more than half a million of weights and several millions of training games. In this work we study the benefits of eligibility traces
more &raquo; ... added to this system. To the best of our knowledge, eligibility traces have not been used before for such a large system. Different versions of eligibility traces (standard, resetting, and replacing traces) are compared. We show that eligibility traces speed up the learning by a factor of two and that they increase the asymptotic playing strength. Thill et al. [1] established a TDL agent for the game Connect-4 solely trained by self-play. Although Connect-4 is
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2014.6932870">doi:10.1109/cig.2014.6932870</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cig/ThillBKK14.html">dblp:conf/cig/ThillBKK14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hkxl4ck76jcxlgfyftp5l5ztie">fatcat:hkxl4ck76jcxlgfyftp5l5ztie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170811063058/http://blogs.gm.fh-koeln.de/konen/files/2014/08/ThillCIG2014.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/81/ed/81edbede36f89aa1be00926a34f13b1457749d9b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2014.6932870"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>