GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
GameHorizon provides 5,000 hours of AAA gameplay data and a benchmark covering 47 models.
GameHorizon Suite measures AI gameplay ability across multiple time horizons. Its dataset contains 5,000 hours of recordings from 21 AAA games, collected by 100 expert players, with aligned video, actions, and multi-horizon instructions. The benchmark supports reproducible offline tests and stepwise online evaluation. The authors tested 47 models through more than one million invocations and plan to release the dataset, annotator, and benchmark.
- Dataset has 5,000 hours from 21 games and 100 players
- Benchmark combines offline questions with stepwise online tests
- Forty-seven models received more than one million evaluations
- Authors plan to release data, annotator, and benchmark
From the original article
1 min read at arxiv.orgModern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, and precise action control over multiple temporal horizons. Existing datasets and benchmarks, however, either cover a narrow range of games, lack language instructions, or rely on high-variance online rollouts.
By Yiran Wang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.