Post #815225

2026-03-27 19:49 UTC

NEW BLOG POST You weren&#39;t doing anything on a Friday afternoon were you? Here&#39;s 4 thousand words about the new and improved Chronicles behavior planning and how I leveraged reinforcement learning techniques used by Chess and Go algorithms to make my baddies smart and efficient. Enjoy! https://blog.brianna.town/the-bigger-better-chronicles-npc-behavior-system #gamedev #indiedev #blog

Replies (6)

@britown@mastodon.gamedev.place 2026-03-30 17:36

the opening paragraphs of this post have been slightly modified for correctness because the original actions post mentioned predated the first working implementation of behavior planning by several months. This bothered nobody but me, please enjoy.

Open ##1716381
@springogeek@mastodon.gamedev.place 2026-03-27 20:40

@britown This is oddly topical for me: I've been noodling around with behaviour planning/selection stuff in my current project for a couple weeks, so it's interesting to see other approaches to it :)

Open ##1716382
@IngloGamesDev@mastodon.gamedev.place 2026-03-28 00:33

@britown excellent article, brought me right back to my graduate algorithms days doing decision trees and alpha/beta pruning :)

Open ##1716385
@kampffrosch@mastodon.gamedev.place 2026-03-28 11:41

@britown Do actors in this system also consider the possible actions of others or just their own?

Open ##1716386
@bbbscarter@mastodon.gamedev.place 2026-03-31 07:56

@britown thanks, that was a great read - using MCTS to coordinate multiple enemy AIs is quite a novel approach! A couple of questions. Do you do anything to simulate the player's move after each step? And how do you 'score' moves like 'block the exit'?

Open ##1716391
@taylorhadden@mastodon.social 2026-03-31 13:55

@britown Lovely read! I hope I can leverage a similar system in the never-future when I’m working on AI!

Open ##1716395