Project „AI Board Game Agent“

Goal: 

The objective of this international team project is the development of an intelligent agent to play the board game Turing Tumble. To explore the game mechanics, we provide a physical version of the game during the project to complement the existing open-source simulator. The game agent should be trained using reinforcement learning in order to solve simple logic challenges building on the implementation of a predecessor project. Thus, the existing approach can be used to get familiar with reinforcement learning and should subsequently be extended. In addition, a UI should be implemented to illustrate the solutions of the agent.  

Setting: 

• 2 students from Mannheim

• 2 students from Cluj-Napoca (Romania)

• 6 months

• 2 collaboration weeks: German students will visit the team in Romania for one week (paid by the university) and the Romanian students will visit the team in Germany for one week

Recommended Skills: 

• We expect that you have programming experience in at least one programming language (e.g. Python)

• We expect basic knowledge of data mining and artificial intelligence (detailed knowledge of reinforcement learning is not expected)