Autonomous-Multi-Agent-exercise
This was a mini-project for the course of Autonomous Agents and Multi-Agent Systems I did in my Masters in Tecnico Lisboa.
The main objective was to study the basic concepts behind individual and multi-agent systems. For this, a basic environment is set up in which agents perform actions and get varying rewards. The agents have to select which actions to take based on their interaction history. Several variations of the basic scenario are proposed. To solve them several optimization problems have to be solved using different techniques.
You can find the project statement in the repository and the respective case studies in the cases directory.