Balancing of competitive two-player Game Levels with Reinforcement Learning
This addresses the labor-intensive process of game level balancing for developers, though it is incremental as it builds on existing PCGRL methods.
The paper tackles the problem of manually balancing competitive two-player game levels by proposing an automated reinforcement learning architecture within the PCGRL framework, showing it can teach an agent to alter levels for balancing better and faster than plain PCGRL.
The balancing process for game levels in a competitive two-player context involves a lot of manual work and testing, particularly in non-symmetrical game levels. In this paper, we propose an architecture for automated balancing of tile-based levels within the recently introduced PCGRL framework (procedural content generation via reinforcement learning). Our architecture is divided into three parts: (1) a level generator, (2) a balancing agent and, (3) a reward modeling simulation. By playing the level in a simulation repeatedly, the balancing agent is rewarded for modifying it towards the same win rates for all players. To this end, we introduce a novel family of swap-based representations to increase robustness towards playability. We show that this approach is capable to teach an agent how to alter a level for balancing better and faster than plain PCGRL. In addition, by analyzing the agent's swapping behavior, we can draw conclusions about which tile types influence the balancing most. We test and show our results using the Neural MMO (NMMO) environment in a competitive two-player setting.