Homework 4

4 minute read

Submission date: March 13th, 2022


  • Deep reinforcement learning based on policy gradients.
  • Image generation with a Variational Autoencoder
  • Generative adversarial networks
  • Course summary questions on various topics.


The assignment is available here (use the download button at the top).

Technical Notes

This assignment requires a different conda environment, which should be installed prior to starting. Before installing the new environment, it is recommended to run

conda update conda
conda config --set channel_priority strict

And then install and activate the new environment as usual,

conda env update -f environment.yml
conda activate cs236781-hw4


Make sure to read the getting started page, the guide for using course servers and our collaboration policy before starting the assignment.

Q: What is the _final checkpoint file?
A: You must use this to create your final submission with result video from your best-trained model. When you get results that your happy with, rename the checkpoint file by appending _final. You don’t need to submit the checkpoints/ folder (the main.py script will ignore them).

Q: Should the results/ directory be part of the submission?
A: Yes. The submission script will include it for you. This is OK. Do not put any unnecessary files in this directory apart from the results files generated by the notebooks.