PlayCraft: Designing Engaging Games from Agent Play Experience
Abstract
PlayCraft uses a vision-based player agent and a crafter agent to iteratively revise games, improving player learning gains and slopes across intelligence settings.
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.
Community
PlayCraft is an automated framework for designing engaging games that give players a path from beginner play to mastery.
PlayCraft alternates between playing and crafting:
A player agent watches the game screen, uses the controls, and pursues the game objective over repeated episodes while retaining memory.
A crafter agent then uses the experience from the player agent to revise the game, aiming to reward better decisions and execution.
Get this paper in your agent:
hf papers read 2611.26624 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper