From 48808c70268a4c043a92efe5ab887e600089c895 Mon Sep 17 00:00:00 2001 From: Jen Looper Date: Tue, 29 Jun 2021 09:49:13 -0400 Subject: [PATCH] editorial for RL --- 8-Reinforcement/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/8-Reinforcement/README.md b/8-Reinforcement/README.md index c9881eb4..ba875d5e 100644 --- a/8-Reinforcement/README.md +++ b/8-Reinforcement/README.md @@ -2,7 +2,7 @@ Reinforcement learning, RL, is seen as one of the basic machine learning paradigms, next to supervised learning and unsupervised learning. RL is all about decisions: delivering the right decisions or at least learning from them. -Imagine you have a simulated environment, like the stock market for example. What happens if you impose this or that regulation does it have a positive or negative effect? The whole point is being able to change course if something negative happen, so called _negative reinforcement_ or if it's a positive outcome, to keep building on that, so called _positive reinforcement_. +Imagine you have a simulated environment such as the stock market. What happens if you impose a given regulation. Does it have a positive or negative effect? If something negative happens, you need to take this _negative reinforcement_, learn from it, and change course. If it's a positive outcome, you need to build on that _positive reinforcement_. ![peter and the wolf](images/peter.png)