arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.04429cs.LGcs.GT
收藏

使用强化学习平衡竞争性双人游戏关卡

Balancing of competitive two-player Game Levels with Reinforcement Learning

University of Applied Sciences Mannheim(曼海姆应用技术大学);Stuttgart Media University(斯图加特媒体大学)

Florian Rupp, Manuel Eberhardinger, Kai Eckert

AI总结:

本文面向双人竞争游戏关卡的自动平衡,在 PCGRL 中引入关卡生成器、平衡智能体与奖励仿真,并通过基于交换的表示提升可玩性鲁棒性,在 NMMO 中验证其优于普通 PCGRL。

摘要:

在竞争性双人情境中,游戏关卡的平衡过程涉及大量人工工作与测试,尤其是在非对称游戏关卡中。本文提出一种架构,用于在近期提出的 PCGRL 框架(通过强化学习进行程序化内容生成)中自动平衡基于图块的关卡。该架构分为三部分:(1)关卡生成器,(2)平衡智能体,以及(3)奖励建模仿真。通过在仿真中反复游玩关卡,平衡智能体若将关卡修改为使所有玩家胜率相同,便会获得奖励。为此,我们引入了一族新颖的基于交换的表示,以增强对可玩性的鲁棒性。我们表明,与普通 PCGRL 相比,该方法能够更好、更快地教会智能体如何修改关卡以实现平衡。此外,通过分析智能体的交换行为,我们可以得出哪些图块类型对平衡影响最大的结论。我们在竞争性双人设置下使用 Neural MMO(NMMO)环境测试并展示了结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑