Date of Award


Document Type

Open Access


Computer Science

First Advisor

TJ Schlueter

Second Advisor

Matthew Anderson




Dungeons and Dragons, Automatic Play-Testing, Game Playing AI, Table Top Role-Playing Games


Dungeons and Dragons is a game where a player, the Game Master / Game Manager (GM), creates content for a set of other players. It is challenging for GMs to predict the difficulty of potential combat encounters. To aid GMs in balancing combat, we create a simulation environment where virtual agents automatically play-test potential encounters and predict difficulty. We implement several agents to simulate human players that fall into two main categories: rule-based agents that follow a pre-made set of rules and general game-playing agents that explore many potential moves. In simple scenarios, rule-based agents win at a higher rate than general agents, but with complex scenarios, the rule-based and general agents perform similarly. These agents interact in a simulated game environment to play-test potential combat encounters. Our results demonstrate that this simulation outputs similar predictions to from base predictions given from the rule-set of DnD. However, in some situations where our simulation deviated from pre-existing predictions, the predictions from experience GMs align more closely with our simulation than existing systems.



Rights Statement

In Copyright - Educational Use Permitted.