Skip to content
arXiv Game World Models & Generation· Jordy Kieto·· 2026-10-06PickAI score71

Ten-hero MOBA continuous Dyna loop study reaches 70.2% radiant-side win rate in real matches

Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA

AI summary

The paper trains a structured multi-agent world model for a full ten-hero MOBA and plugs it into a continuous asynchronous Dyna loop; policies learn only from 1,400-tick imagined matches and win 70.2% of real matches as radiant (421 wins in 600 games, 95% CI 66.4-73.7), win none as dire, and also lose every game against the built-in opponent in self-play.

Why it matters

The paper evaluates the world model in real matches; the Dyna loop raises the radiant-side win rate from 33.7% to 70.2%, and the model and evaluation protocol are open-sourced.

Source: arXiv Game World Models & Generation · arxiv.org