chasemc67 / Mathematical_Functions_Reinforcement_Learning

Learning a mathematical function with reinforcement learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Learning a Mathematical Function through Reinforcement Learning

Agent learns the function target = sin(x − 3) cos(y) + N(0, 0.1), where N is randomly destributed with mean = 0 and standard dev = 0.1

screen shot 2018-05-13 at 8 09 20 pm

screen shot 2018-05-13 at 8 11 03 pm

Requirements:

python 2.7
conda install matplotlib

Installing Requirements:

conda create --name python27 python=2.7
source activate python27
conda install matplotlib

Usage:

python SuperLearn.py

should output f10000

Plotting:

python2 plot.py f10000

This is an assignment from a class on Reinforcement Learning, taught by Richard Sutton, the father of Reinforcement Learning

About

Learning a mathematical function with reinforcement learning


Languages

Language:Python 100.0%