Skip to content

Latest commit

 

History

History
39 lines (25 loc) · 1.2 KB

File metadata and controls

39 lines (25 loc) · 1.2 KB

An Implementation of World Models in TensorFlow

dep2 dep1 dep2

car-driving

Medium Article

Please read more about this implementation on my article World Models in TensorFlow — Episode 1

Create a Python Virtual Environment

mkvirtualenv --python=/usr/bin/python3 World-Models-TensorFlow

Install dependencies

sudo apt-get install -y python-numpy python-dev cmake zlib1g-dev libjpeg-dev xvfb libav-tools xorg-dev python-opengl libboost-all-dev libsdl2-dev swig

pip install -r requirements.txt

1. Stateless Agents

Train the agents to drive around using only the information from the current frame.

cd stateless_agent/

And follow the instructions there

2. Train the RNN

Work in Progress

3. ....