--- format: "aidr-story-markdown/v1" id: "db6f0f806d3316e18c73c4f315574495d82af3dfa85afe98bd916409c40d04a8" canonical_url: "https://aidr.today/db6f0f80?lang=en" title: "GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-11-12T00:00:00.000Z" category: "Frameworks" topics: ["agent","framework"] source_urls: ["https://huggingface.co/papers/2611.13028"] summary: "GTAGym is a new environment and framework for evaluating and applying reinforcement learning to GTA V tasks. Its GTAVBench benchmark includes 103 online tasks from GTA V main-story missions across nine task families and 47 image-based shooting and sniping tasks. A web server supports parallel testing via screenshots and keyboard-mouse actions with automatic engine-state outcome checks. Six frontier LLMs were evaluated on GTAVBench and its GTAVBench-AGI branch, with the best configuration achieving 70.9% overall accuracy in GTAVBench-AGI." --- # GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning > [Open the canonical story]() **Published:** 2026-11-12T00:00:00.000Z **Category:** Frameworks **Topics:** agent, framework ## Summary GTAGym is a new environment and framework for evaluating and applying reinforcement learning to GTA V tasks\. Its GTAVBench benchmark includes 103 online tasks from GTA V main\-story missions across nine task families and 47 image\-based shooting and sniping tasks\. A web server supports parallel testing via screenshots and keyboard\-mouse actions with automatic engine\-state outcome checks\. Six frontier LLMs were evaluated on GTAVBench and its GTAVBench\-AGI branch, with the best configuration achieving 70\.9% overall accuracy in GTAVBench\-AGI\. ## Sources - [Story source]()