Loading

Accessibility

Option Missing?
Leave Feedback

Extended Project Qualification (EPQ)

schedule
1 Year
person
Solo

Skills Used:

Python Logo
Python
Tensorflow Logo
Tensorflow

During my A levels I completed an award winning A* EPQ. This is a dissertation equivalent to half an A level. For the topic of my EPQ, I chose to continue a personal project, developing machine learning.

An AI that uses a combination of multiple learning techniques, is better than an AI that uses only one learning technique.

I developed a multi-technique learning AI agent for supervised learning that works on reinforcement tasks.
This works by watching humans play each other, or from creating its own data-set using brute force, or by using an existing data-set.

Once a data-set is created it then uses stochastic gradient descent to train a neural network. When the error of the data-set is low enough, evolution then takes over the learning of the network to allow the agent to improve beyond the starting data-set. This learned all the tasks I tested it on faster with more accuracy and reliability than the other AI agents at the time.

Cart Pole

This is one of many reinforcement learning environments I used from OpenAI's Gym

No Training

Training mid point

End of Training

Time To Learn

EvolutionBrute ForceCombinedRandom
CartPole20N/A5N/A
Simple Dataset3.56.52.5N/A
Complex DatasetN/A4628N/A
Tic Tac ToeN/A240150N/A