Authors: Gianvito Losapio, Marco Mussi, Alberto Maria Metelli, Marcello Restelli
The code is composed of two different folders, each containing a specific algorithm implementation.
- 📂 distributed_q_learning contains the code for the Distributed Q Learning algorithm (DQL)
- 📂 state_action_factorization contains the code for the State and Action Factorization algorithm (SAF)
A description of how to use the code is provided separately in the README file of each folder.