{"id":673,"date":"2026-05-04T23:06:37","date_gmt":"2026-05-05T03:06:37","guid":{"rendered":"http:\/\/stephendavies.org\/data420\/?p=673"},"modified":"2026-05-04T23:17:14","modified_gmt":"2026-05-05T03:17:14","slug":"rules-based-contents-results","status":"publish","type":"post","link":"http:\/\/stephendavies.org\/data420\/index.php\/2026\/05\/04\/rules-based-contents-results\/","title":{"rendered":"Rules-based contents results"},"content":{"rendered":"<p>I&#8217;ve decided to first run all the rules-based players by themselves, then do LLMs after that (time-permitting).<\/p>\n<p>Here are the official rules-based-players-only results (I ran <strong>50<\/strong> simulations for <strong>500<\/strong> iterations each, and averaged all the results):<\/p>\n<style type=\"text\/css\">\ntable td:nth-child(2),\ntable td:nth-child(3),\ntable th:nth-child(2),\ntable th:nth-child(3) {\n  text-align: center;\n}\ntable td:nth-child(1) { font-family:monospace; }\n.winner {font-size:large;font-weight:bold;color:#DAA520;}\n.pts {color:darkred;font-weight:bold;}\n<\/style>\n<table border=1 cellspacing=5 cellpadding=5>\n<tr>\n<th>Player<\/th>\n<th>Avg winnings<\/th>\n<th>Avg node degree<\/th>\n<\/tr>\n<tr>\n<td><b>A\u1d40<\/b><\/td>\n<td>626.181<\/td>\n<td>11.61<\/td>\n<\/tr>\n<tr>\n<td><b>Smooth Criminal<\/b><\/td>\n<td>625.379<\/td>\n<td>8.02<\/td>\n<\/tr>\n<tr>\n<td><b>suspiciouslyOdd<\/b><\/td>\n<td>618.934<\/td>\n<td>2.28<\/td>\n<\/tr>\n<tr>\n<td><b>Pocoyo<\/b><\/td>\n<td>552.462<\/td>\n<td>7.50<\/td>\n<\/tr>\n<tr>\n<td>Sucker<\/td>\n<td>545.710<\/td>\n<td>8.00<\/td>\n<\/tr>\n<tr>\n<td><b>CaffieneAddict<\/b><\/td>\n<td>511.135<\/td>\n<td>7.63<\/td>\n<\/tr>\n<tr>\n<td><b>ColmTheGOAT<\/b><\/td>\n<td>504.759<\/td>\n<td>7.96<\/td>\n<\/tr>\n<tr>\n<td><b>MyNameIsRetep<\/b><\/td>\n<td>485.058<\/td>\n<td>7.57<\/td>\n<\/tr>\n<tr>\n<td><b>Goblin<\/b><\/td>\n<td>480.656<\/td>\n<td>7.98<\/td>\n<\/tr>\n<tr>\n<td>Browser<\/td>\n<td>470.466<\/td>\n<td>6.51<\/td>\n<\/tr>\n<tr>\n<td>Mean<\/td>\n<td>440.548<\/td>\n<td>7.99<\/td>\n<\/tr>\n<tr>\n<td><b>Stephen Davies<\/b> <i>(not the real one)<\/i><\/td>\n<td>429.481<\/td>\n<td>5.87<\/td>\n<\/tr>\n<tr>\n<td>TitForTat<\/td>\n<td>392.847<\/td>\n<td>8.00<\/td>\n<\/tr>\n<tr>\n<td><b>GrilledCheeseSandwich<\/b><\/td>\n<td>338.137<\/td>\n<td>7.98<\/td>\n<\/tr>\n<tr>\n<td><b>Evenstar<\/b><\/td>\n<td>313.667<\/td>\n<td>2.65<\/td>\n<\/tr>\n<tr>\n<td><b>Peachy Pearl<\/b><\/td>\n<td>200.039<\/td>\n<td>3.85<\/td>\n<\/tr>\n<tr>\n<td><b>Al-Khwarizmi_<\/b><\/td>\n<td>-1840.430<\/td>\n<td>16.13<\/td>\n<\/tr>\n<tr>\n<td><b>StrawberryFinch<\/b><\/td>\n<td>-2228.890<\/td>\n<td>23.97<\/td>\n<\/tr>\n<\/table>\n<p>That last column is the <i>average degree of the player&#8217;s node in the network at simulation&#8217;s end<\/i>. I find that a fascinating column. One might think: &#8220;having too many friends is a recipe for failure,&#8221; given the large degree averages of the players at the bottom end of the scale. However, the big housefly in that ointment, of course, is that the <i>winner<\/i> of the competition (<tt class=\"winner\">A\u1d40<\/tt>) had quite a <i>high<\/i> average degree.<\/p>\n<p>Here&#8217;s a scatterplot of the results (omitting the outliers) if you&#8217;re interested. There are apparently multiple very different paths to victory: just look at the top three finishers!<\/p>\n<div style=\"border:1px solid black; text-align:center;\">\n  <a href=\"winners_plot.png\"><br \/>\n   <img decoding=\"async\" style=\"width:600px;\" src=\"winners_plot.png\" \/><br \/>\n  <\/a>\n<\/div>\n<p>Here&#8217;s one sample run (37 of 50, I believe) which is interesting to watch. (<tt>MartyMauser<\/tt> does particularly well in this one, but of course it&#8217;s the overall performance over many seeds that takes the cake.)<\/p>\n<div style=\"border:3px solid black; text-align:center;\">\n  <a href=\"sample_rules_based_run.mp4\"><br \/>\n   <img decoding=\"async\" style=\"width:500px;\" src=\"sample_rules_based_run_frame.png\" \/><br \/>\n  <\/a>\n<\/div>\n<p>At any rate, I award the following points:<\/p>\n<ul>\n<li><span class=\"pts\">+40XP<\/span> to the nine players who beat <tt>TitForTat<\/tt><\/li>\n<li><span class=\"pts\">+30XP<\/span> to the five players who didn&#8217;t<\/li>\n<li><span class=\"pts\">+100XP<\/span> to <tt class=\"winner\">A\u1d40<\/tt>&#8216;s final exam score (capped at <span class=\"pts\">100XP<\/span>)<\/li>\n<li><span class=\"pts\">+50XP<\/span> to <tt class=\"winner\">Smooth Criminal<\/tt>&#8216;s final exam score (capped at <span class=\"pts\">100XP<\/span>)<\/li>\n<li><span class=\"pts\">+20XP<\/span> to <tt class=\"winner\">suspiciouslyOdd<\/tt>&#8216;s final exam score (capped at <span class=\"pts\">100XP<\/span>)<\/li>\n<li><span class=\"pts\">+10XP<\/span> to <tt class=\"winner\">Pocoyo<\/tt>&#8216;s final exam score (capped at <span class=\"pts\">100XP<\/span>)<\/li>\n<\/ul>\n<p>Congratulations to all our winners! And now on to the LLM competition&#8230;*(pant, pant)*<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I&#8217;ve decided to first run all the rules-based players by themselves, then do LLMs after that (time-permitting). Here are the official rules-based-players-only results (I ran 50 simulations for 500 iterations each, and averaged all the results): Player Avg winnings Avg node degree A\u1d40 626.181 11.61 Smooth Criminal 625.379 8.02 suspiciouslyOdd 618.934 2.28 Pocoyo 552.462 7.50 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[1],"tags":[],"class_list":["post-673","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/posts\/673","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/comments?post=673"}],"version-history":[{"count":13,"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/posts\/673\/revisions"}],"predecessor-version":[{"id":686,"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/posts\/673\/revisions\/686"}],"wp:attachment":[{"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/media?parent=673"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/categories?post=673"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/stephendavies.org\/data420\/index.php\/wp-json\/wp\/v2\/tags?post=673"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}