Saved in:
Bibliographic Details
Main Author: Wang, Xiaoxi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.12557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913218379644928
author Wang, Xiaoxi
author_facet Wang, Xiaoxi
contents When training artificial intelligence for games encompassing multiple roles, the development of a generalized model capable of controlling any character within the game presents a viable option. This strategy not only conserves computational resources and time during the training phase but also reduces resource requirements during deployment. training such a generalized model often encounters challenges related to uneven capabilities when controlling different roles. A simple method is introduced based on Regret Matching+, which facilitates a more balanced performance of strength by the model when controlling various roles.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12557
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Balancing the AI Strength of Roles in Self-Play Training with Regret Matching+
Wang, Xiaoxi
Artificial Intelligence
When training artificial intelligence for games encompassing multiple roles, the development of a generalized model capable of controlling any character within the game presents a viable option. This strategy not only conserves computational resources and time during the training phase but also reduces resource requirements during deployment. training such a generalized model often encounters challenges related to uneven capabilities when controlling different roles. A simple method is introduced based on Regret Matching+, which facilitates a more balanced performance of strength by the model when controlling various roles.
title Balancing the AI Strength of Roles in Self-Play Training with Regret Matching+
topic Artificial Intelligence
url https://arxiv.org/abs/2401.12557