Skip to content
arXiv Game AI· Kailing Li·· 19 d agoSame newsAI score41

AceAction-5M: A dataset for hierarchical-goal generalist action learning across multiple 3D game worlds

AceAction-5M: Hierarchical Goals for Generalist Action Learning Across 3D Game Worlds

AI summary

The authors present the AceAction dataset, a collection of human gameplay demonstrations across multiple 3D games that links overall task instructions, ordered subgoals and local skill instructions with time-aligned visual observations and keyboard-and-mouse actions, covering navigation, reconnaissance, combat, interaction and recovery. The team uses a vision-language model pipeline to identify subgoals from changes in goals or interactable objects, anchor navigation goals to recognizable waypoints, and compose adjacent subgoals into task instructions. Review of 500 trajectories achieved a 95.8% pass rate in independent evaluation.

Same news; Picks shows “AceAction-5M: A dataset for hierarchical-goal generalist action learning across multiple 3D game worlds”

Source: arXiv Game AI · arxiv.org