GTAGym:用于评估与强化学习的 AAA 游戏任务环境

媒体报道 Hugging Face Papers 原文语言:中文

GTAGym 构建了基于 GTA V 主线任务的评估基准 GTAVBench,包含 103 项任务和 47 项图像射击任务,并提供网页服务器实现并行截图与键鼠交互。六种前沿大语言模型在 GTAVBench‑AGI 上最高达 70.9% 准确率,航行、规避和拦截仍具挑战。LoRA 强化学习 Qwen 3.8‑27B 在生成的步行导航任务上提升了 15%‑23% 的性能,并实现跨任务迁移。

全文

AAA games offer a rich testbed for evaluating agent perception, reasoning, and control. However, evaluating whether agents can complete tasks in AAA games is challenging and often human-annotated because task outcomes are often difficult to verify automatically, let alone applying it for Reinforcement Learning (RL). We introduce GTAGym, an environment and framework for evaluation and RL on GTA V tasks. Its evaluation benchmark, GTAVBench, derived from GTA V main-story missions, contains 103 online tasks reconstructed across nine task families, alongside 47 image-based shooting and sniping tasks using GTA V imagery. A web server provides access to the online environment and evaluation interface, supporting parallel testing through screenshots and keyboard-mouse actions with automatic engine-state outcome checks. We evaluate six frontier LLMs on GTAVBench with textual task instructions and on its GTAVBench-AGI branch, where instructions appear only in the first screenshot and a harness automatically compresses interaction history. The best configuration achieves 70.9% overall accuracy in GTAVBench-AGI, yet aerial navigation, evasion and interception remain difficult. GTAGym also provides a scalable generator that samples task parameters within user-specified ranges and option sets under fixed templates, creating batches of 3D and image-based shooting environments for RL with automatic reward and termination signals. LoRA RL of Qwen3.8-27B on generated on-foot navigation tasks improves the in-domain performance and transfers to out-of-domain task categories, and native GTA V tasks from 15% to 23%.

View arXiv page View PDF GitHub 11 Add to collection

正文以来源语言显示。

参考来源

← 返回每日AI报告