Skip to content

Proximal Policy Optimisation (PPO) PyTorch implementation for the inverted double pendulum problem.

Notifications You must be signed in to change notification settings

mughees-asif/dip

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Reinforcement Learning for Robotic Systems

Notes

  • GitHub has an ongoing problem rendering Jupyter Notebooks. Please view the final notebook version here.
  • To read the accompanying written evaluation, please see this.
  • For a quick overview, check out this.

Environment Setup

  • Install Miniconda: https://docs.conda.io/en/latest/miniconda.html
  • Open terminal: git clone git@github.com:mughees-asif/dip.git
  • Create new environment [enter custom name instead of <ENV_NAME>] in the same directory through the Miniconda terminal: conda create -n <ENV_NAME> python sympy numpy matplotlib
  • Install PyTorch: https://pytorch.org/get-started/locally/
  • Install Jupyter Notebook: conda install -c conda-forge notebook
  • Navigate to the environment directory & open this notebook through the Miniconda terminal: jupyter notebook
  • You should now be set-up to run this example
  • Any problems: email me