Authors: Michele Conti and Luca Iezzi.

Codebase for the Deep Learning and Applied AI course project at Sapienza University of Rome (ay 2020/2021). This consists of a reimplementation of World Models, and its adaptation on Plunder, one of the environments from Procgen Benchmark.

Agent playing

This implementation is based on Python 3.8. To install all the requirements:

$ pip install -r requirements.txt

The complete pipeline to train the 3 model components:

First, we generate 1000 rollouts from a random policy:

$ PYTHONPATH=. python3 src/generate_data.py --rollouts 1000

We then split the data in train, validation, and test:

$ PYTHONPATH=. python3 src/split_data.py

Finally, we reorganize the data in order to train the MDN-RNN:

$ PYTHONPATH=. python3 src/pl_data/new_dataset.py

To train the Vision, set config_name="vae" in line 149 of the run.py script, then run the following:

$ PYTHONPATH=. python3 src/run.py

To train the Memory, set config_name="mdrnn" in line 149 of the run.py script, then run the following:

$ PYTHONPATH=. python3 src/run.py

To train the Controller, run the following:

$ PYTHONPATH=. python3 src/controller.py

We took inspiration from the implementations of Corentin Tallec and Sebastian Risi.