Evaluating Environments Using Exploratory Agents
Bobby Khaleque, Mike Cook, Jeremy Gow
TL;DR
The paper addresses evaluating the exploratory quality of procedurally generated game levels using an exploratory agent. It introduces an agent framework with direction- and object-based metrics (coverage, inspection, entropy, novelty, motivation) and a fitness function to rate levels produced by two WFC-based generators. Experimental results show the agent can distinguish engaging versus unengaging levels, with higher motivation, novelty, and overall fitness in engaging levels, suggesting the agent’s potential as a PCG evaluation tool. The work advances AI-driven game design by providing objective feedback that can guide generation toward exploration-rich environments.
Abstract
Exploration is a key part of many video games. We investigate the using an exploratory agent to provide feedback on the design of procedurally generated game levels, 5 engaging levels and 5 unengaging levels. We expand upon a framework introduced in previous research which models motivations for exploration and introduce a fitness function for evaluating an environment's potential for exploration. Our study showed that our exploratory agent can clearly distinguish between engaging and unengaging levels. The findings suggest that our agent has the potential to serve as an effective tool for assessing procedurally generated levels, in terms of exploration. This work contributes to the growing field of AI-driven game design by offering new insights into how game environments can be evaluated and optimised for player exploration.