GTAGym:用於評測及強化學習的 AAA 遊戲任務環境
GTAGym: AAA Game Tasks Environment for Evaluation and Reinforcement Learning
GTAGym 提供一套以 GTA V 任務為基礎的評測及強化學習環境,並設有 GTAVBench 基準。GTAVBench 包含九類共 103 個線上任務,以及 47 個使用 GTA V 圖像的射擊和狙擊任務;六款前沿大語言模型在 GTAVBench-AGI 的最佳整體準確率為 70.9%。
Abstract
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 Add to collection
Get this paper in your agent:
hf papers read 2611.13028
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
Cite arxiv.org/abs/2611.13028 in a model README.md to link it from this page.
Datasets citing this paper 1
OpenMOSS-Team/GTAVBench
Viewer • Updated 1 day ago • 150 • 53 • 3
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.13028 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co