arXiv Artificial Intelligence

Game-Agnostic Value Functions through Automatic JSON Feature Extraction

10 days ago 01.09.2026 07:00 👁 2 views
Game-Agnostic Value Functions through Automatic JSON Feature Extraction

Quick summary

arXiv:2608.30056v1 Announce Type: new Abstract: JSON Bag-of-Tokens (JSON-Bag) is a recently proposed method to generically represent game trajectories by tokenizing their JSON descriptions. We introduce JSON-Bag VF, a game-agnostic approach to training value functions for game-playing agents using JSON-Bag prototypes. We show that this approach can be enhanced with Random Forest-based feature selection and a method to select game-stage-specific features. We evaluate JSON-Bag VF with One-step-look-ahead (JSON-Bag OSLA) on six tabletop games over different combinations of prototype-tokenization

Key takeaways

  • arXiv:2608.30056v1 Announce Type: new Abstract: JSON Bag-of-Tokens (JSON-Bag) is a recently proposed method to generically represent game trajectories by tokenizing their JSON descriptions.
  • We introduce JSON-Bag VF, a game-agnostic approach to training value functions for game-playing agents using JSON-Bag prototypes.
  • We show that this approach can be enhanced with Random Forest-based feature selection and a method to select game-stage-specific features.

Why it matters

This development shows AI moving deeper into everyday software. Productivity potential should be weighed against price, data permissions, exportability and the preservation of human control.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗