https://blog.lukesalamone.com/tags/multi-agent-rl/ Recent content in Multi-Agent-Rl on Luke Salamone's Blog Hugo en-us Mon, 08 Jun 2026 00:20:43 -0700 https://blog.lukesalamone.com/posts/fighting-game-rl/ Mon, 08 Jun 2026 00:20:43 -0700 https://blog.lukesalamone.com/posts/fighting-game-rl/ <script type="text/javascript" async src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.7/MathJax.js?config=TeX-MML-AM_CHTML"></script> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ tex2jax: { inlineMath: [['$','$'], ['\\(','\\)']], displayMath: [['$$','$$'], ['\[','\]']], processEscapes: true, processEnvironments: true, skipTags: ['script', 'noscript', 'style', 'textarea', 'pre'], TeX: { equationNumbers: { autoNumber: "AMS" }, extensions: ["AMSmath.js", "AMSsymbols.js"] } } }); </script> <script type="text/x-mathjax-config"> MathJax.Hub.Queue(function() { var all = MathJax.Hub.getAllJax(), i; for(i = 0; i < all.length; i += 1) { all[i].SourceElement().parentNode.className += ' has-jax'; } }); </script> <p>In this project, I wanted to set up what I thought was a simple experiment: if we let a neural network play a fighting game, will it learn any interesting emergent behaviors? I would say the answer is a resounding &ldquo;kind of&rdquo;. The players will find &ldquo;optimal&rdquo; strategies, but whether we see those optimal strategies as interesting or simply as hacks is a bit of a matter of opinion.</p>