Teaching an agent to balance a pole on a cart using Policy Gradient Reinforcement Learning with Tensorflow and OpenAI-gym
To do this in University of Hyderabad SCIS gpu as jupyter-notebook rendering, see this to know how to take out the rendering of the environment as a video. Do this on #source env/bin/activate only! https://star-ai.github.io/Rendering-OpenAi-Gym-in-Colaboratory/ Works in colab too
!pip install gym !pip install --upgrade pip !pip install tensorflow-gpu==1.15