about
AI and Wargaming (arxiv.org)
2 points by homarp on Sep 22, 2020 | hide | past | pdf | discuss on HN

In plain words: A survey of game AI successes—machines that beat top humans at Go and StarCraft using lots of play data or practice—asks what makes wargames different from those games. It then matches the best-fitting recent AI advances to those differences.

Abstract

Recent progress in Game AI has demonstrated that given enough data from human gameplay, or experience gained via simulations, machines can rival or surpass the most skilled human players in classic games such as Go, or commercial computer games such as Starcraft. We review the current state-of-the-art through the lens of wargaming, and ask firstly what features of wargames distinguish them from the usual AI testbeds, and secondly which recent AI advances are best suited to address these wargame-specific features.

James Goodman, Sebastian Risi, Simon Lucas
arXiv:2009.08922 · cs.AI · submitted Sep 18, 2020 · updated Sep 25, 2020
abstract · pdf · html

add comment on HN
Also discussed: Sep 2020 (1 point, 0 comments)