用强化学习自动平衡非对称游戏关卡，提升公平性。
Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning
- 基于强化学习的关卡生成与调整框架，通过模拟反馈优化平衡性。
- 在NMMO环境中实现双方胜率接近50%，优于传统搜索方法。
- 可分析关键地块影响，适用于多种公平性目标，适合游戏开发者参考。
在竞争性双人游戏中，非对称关卡的平衡需要大量人工测试和调优。本文将关卡平衡视为程序化内容生成任务，在PCGRL框架下提出一种自动平衡瓦片式关卡的架构。该架构包含三部分：关卡生成器、平衡代理和奖励建模仿真器。通过反复仿真，代理根据调整结果获得奖励，以逼近预设平衡目标（如双方胜率相等）。为此，我们提出基于交换的表示方法，增强可玩性鲁棒性，使代理更高效地完成平衡任务。通过分析代理的交换行为，可识别对平衡影响最大的地块类型。我们在神经多玩家环境（NMMO）中验证了该方法在双人竞争场景下的有效性。本扩展版论文展示了改进结果，探索了除均等平衡外的其他平衡形式，对比了另一种搜索方法，并讨论了现有公平性度量在游戏平衡中的应用。
原文摘要 · Abstract (English)
The balancing process for game levels in competitive two-player contexts involves a lot of manual work and testing, particularly for non-symmetrical game levels. In this work, we frame game balancing as a procedural content generation task and propose an architecture for automatically balancing of tile-based levels within the 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. Through repeated simulations, the balancing agent receives rewards for adjusting the level towards a given balancing objective, such as equal win rates for all players. To this end, we propose new swap-based representations to improve the robustness of playability, thereby enabling agents to balance game levels more effectively and quickly compared to traditional PCGRL. By analyzing the agent's swapping behavior, we can infer which tile types have the most impact on the balance. We validate our approach in the Neural MMO (NMMO) environment in a competitive two-player scenario. In this extended conference paper, we present improved results, explore the applicability of the method to various forms of balancing beyond equal balancing, compare the performance to another search-based approach, and discuss the application of existing fairness metrics to game balancing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。