Update README.md

Author: boraakoguz

README.md

@@ -2,12 +2,32 @@
 
 A Generative Algorithm AI implementation on a 2D racing simulator "Java Racer" (https://github.com/boraakoguz/JavaRacer)
 
+## Features
+The algorithm features:
+- Elitism 
+- Cross-over succession depending on the success of the parents
+- Mutation 
+- Advanced mutation techniques to improve variation 
+- A roll-back mechanism in order to prevent bad training.
+
+Project features:
+- Custom map/track design
+- Save mechanism
+- Live data on the screen
+
+Live Data meanings:
+- Best Fit: The most points scored by an agent of the previous generation
+- Gen. No: The number of generations
+- Instruction Size: The length of the instruction array used by the agents that gradually expands
+- Last Increase Points: The maximum points scored by an agent at the previous Instruction array expansion. Serves as a benchmark and controlls the roll-back system, advanced mutation system and stops Instruction increase in case of failure to pass the benchmark. 
+
 ## Screen Shots
 A screenshot from the training process
 ![screenshot](https://github.com/boraakoguz/JavaRacer-generative-algorithm/blob/main/screenshots/screenshot1.png)
 
 
 ![gif](https://github.com/boraakoguz/JavaRacer-generative-algorithm/blob/main/screenshots/example.gif)
+
 A gif of the start of a half-completed training
 
 ## Creating a Track