Researchers have developed a framework called Script2Play that automates the training of vision-language-action (VLA) models for gameplay. This system uses a large language model to generate game environments and expert demonstrations, bypassing the need for human gameplay data. Script2Play, a 4B vision-language model, was trained on 150.3 hours of synthetic gameplay in Minecraft and Roblox, demonstrating effective instruction following and generalization across different game engines. AI
IMPACT Automates VLA model training, potentially reducing costs and accelerating development for AI agents in gaming and simulation environments.
RANK_REASON The cluster describes a research paper detailing a new framework and model for training AI agents. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →