PlayCraft:用视觉智能体试玩游戏并自动打磨难度曲线
PlayCraft: Designing Engaging Games from Agent Play Experience
让视觉智能体实际试玩游戏,把试玩报告交给另一个智能体改游戏难度曲线,专治 AI 生成游戏“能玩但无聊”。做了学习增益和学习斜率量化评测,三个智能水平都跑赢基线,做游戏生成和关卡设计的人可以直接参考它的评测思路。
arXiv 论文 PlayCraft 提出一个自动化框架,专门解决 AI 生成游戏“能玩但不好玩”的问题,核心切入点是掌握感(mastery)这一玩家投入度来源。框架包含两个阶段:playing 阶段由一个基于视觉的玩家智能体观看游戏画面、操作控制、重复多个 episode 并保留记忆,每次结束后输出进度、结果、决策和反思报告;crafting 阶段由 crafter 智能体根据这些报告修订游戏,估算玩家能力、预测不同熟练度下的表现,并与目标学习曲线对比,找出差距后通过调整设计让玩家有通过更好决策和执行来提升的空间。
评估采用三个不同智能水平的玩家智能体在全新运行中测试,指标为学习增益(learning gain)和学习斜率(learning slope)。结果显示,与初始游戏相比,PlayCraft 修订后的游戏在大多数游戏中学习增益更大、学习斜率更陡,并且在每个智能水平设置下的两项指标宏平均上都优于基线方法。
PlayCraft: Designing Engaging Games from Agent Play Experience
Recent AI agents can generate playable games, but these games are not necessarily engaging. Mastery is a key source of engagement, yet designing for it requires extensive human play and tuning. We propose PlayCraft, an automated framework that uses a vision-based agent to play games and draws on its detailed play experience to revise them for mastery. Starting from an initial game, PlayCraft alternates between playing and crafting. In the playing stage, a player agent watches the game screen, uses the controls, and pursues the game objective over repeated episodes while retaining memory. After each episode, it reports its progress, outcomes, decisions, and reflections. In the crafting stage, a crafter agent uses these reports to revise the game. It estimates player abilities, predicts performance at different proficiency levels, and compares those predictions with a target learning progression. It diagnoses the game and addresses the gaps by giving players meaningful opportunities to improve through better decisions and execution. We evaluate games in fresh runs with player agents across three intelligence settings, measuring learning gain and learning slope. Compared with the initial games, PlayCraft yields larger learning gains and steeper learning slopes in most games. It also outperforms the baselines on the macro-average of each metric at every intelligence setting.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include PlayCraft, game generation, agents, arXiv.
Source attribution: curated from arXiv cs.AI (@Weihao Cheng).