From b46d6795a32676e759328d7aa1b548e6e3c7dc44 Mon Sep 17 00:00:00 2001
From: ben-jaynes <1btjaynes@gmail.com>
Date: Thu, 4 Jun 2026 18:49:04 -0700
Subject: [PATCH] vault backup: 2026-06-04 18:49:04

---
 .../Class 6-4 (Reinforcement Learning).md                      | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Running Start/CSB320 - Machine Learning Concepts/Class 6-4 (Reinforcement Learning).md b/Running Start/CSB320 - Machine Learning Concepts/Class 6-4 (Reinforcement Learning).md
index 81c4a3f..4dce4b2 100644
--- a/Running Start/CSB320 - Machine Learning Concepts/Class 6-4 (Reinforcement Learning).md	
+++ b/Running Start/CSB320 - Machine Learning Concepts/Class 6-4 (Reinforcement Learning).md	
@@ -14,4 +14,7 @@
 		- $\varepsilon$ often starts high and decreases over time
 	- $\rho$ (regret) can be used to find how good a strategy is
 		- this is the difference between how much reward was gotten and the maximum reward possible if distributions are known ahead of time
+- markov decision process
+	- future states only depend on the present state, not what came before
+	- trying to maximize reward without knowing entire history
 	- 
\ No newline at end of file