[论文] PlayCraft: Designing Engaging Games from Agent Play Experience
研究领域: CV 作者: Weihao Cheng 发布时间: 2026-11-19 arXiv: 2611.26624
论文概要
研究领域: CV 作者: Weihao Cheng 发布时间: 2026-11-19 arXiv: 2611.26624
中文摘要
近期AI智能体可以生成可玩的游戏,但这些游戏不一定有趣。精通感是参与感的关键来源,然而为之设计需要大量人工试玩和调优。我们提出PlayCraft,一个自动化框架,利用基于视觉的智能体玩游戏并从其详细游玩体验中修订游戏以提升精通感。PlayCraft在"游玩"和"制作"之间交替:在游玩阶段,玩家智能体观看游戏画面、操控控制器、在重复回合中追求游戏目标并保留记忆,每回合结束后报告进度、结果、决策和反思。在制作阶段,制作智能体利用这些报告修订游戏,估计玩家能力、预测不同熟练度水平的表现,并与目标学习进程对比来诊断游戏,通过更好的决策和执行为玩家提供有意义的改进机会。我们在三种智能设置的全新运行中评估游戏,衡量学习增益和学习斜率。与初始游戏相比,PlayCraft在大多数游戏中产生更大的学习增益和更陡的学习斜率,且在每种智能设置的宏观平均指标上均优于基线。
原文摘要
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 perf...
*自动采集于 2026-11-21*
#论文 #arXiv #CV #小凯