procedural-content-generation

Introduces a novel 'cake' representation for game levels over time that implicitly encodes dynamic information, along with a generative approach (Playtrace Reconstructive Partitioning, PRP) that outperforms six state-of-the-art PCG methods in Sokoban by producing valid levels without sacrificing solution diversity.

This paper explores three novel approaches for procedurally generating enemy morphologies (body plans and collision information) specifically conditioned on player collision interactions, finding all outperform an evolutionary baseline adapted from robotics.

This paper proposes a hybrid method combining Wave Function Collapse (WFC) and reinforcement learning to generate game levels that are both visually satisfying and playable, using WFC constraints to guide the RL agent.