Saved in:
Bibliographic Details
Main Authors: Liu, Tian, Cann, Alex, Colbert, Ian, Saeedi, Mehdi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.14154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909849689784320
author Liu, Tian
Cann, Alex
Colbert, Ian
Saeedi, Mehdi
author_facet Liu, Tian
Cann, Alex
Colbert, Ian
Saeedi, Mehdi
contents While the rapid advancements in the reinforcement learning (RL) research community have been remarkable, the adoption in commercial video games remains slow. In this paper, we outline common challenges the Game AI community faces when using RL-driven NPCs in practice, and highlight the intersection of RL with traditional behavior trees (BTs) as a crucial juncture to be explored further. Although the BT+RL intersection has been suggested in several research papers, its adoption is rare. We demonstrate the viability of this approach using AMD Schola -- a plugin for training RL agents in Unreal Engine -- by creating multi-task NPCs in a complex 3D environment inspired by the commercial video game ``The Last of Us". We provide detailed methodologies for jointly training RL models with BTs while showcasing various skills.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Schola
Liu, Tian
Cann, Alex
Colbert, Ian
Saeedi, Mehdi
Artificial Intelligence
Machine Learning
While the rapid advancements in the reinforcement learning (RL) research community have been remarkable, the adoption in commercial video games remains slow. In this paper, we outline common challenges the Game AI community faces when using RL-driven NPCs in practice, and highlight the intersection of RL with traditional behavior trees (BTs) as a crucial juncture to be explored further. Although the BT+RL intersection has been suggested in several research papers, its adoption is rare. We demonstrate the viability of this approach using AMD Schola -- a plugin for training RL agents in Unreal Engine -- by creating multi-task NPCs in a complex 3D environment inspired by the commercial video game ``The Last of Us". We provide detailed methodologies for jointly training RL models with BTs while showcasing various skills.
title Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Schola
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.14154