Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Wuzhou, Li, Siyi, Zou, Qingxiang, Liao, Zixing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.12098
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915257679609856
author Sun, Wuzhou
Li, Siyi
Zou, Qingxiang
Liao, Zixing
author_facet Sun, Wuzhou
Li, Siyi
Zou, Qingxiang
Liao, Zixing
contents In various game scenarios, selecting a fixed number of targets from multiple enemy units is an extremely challenging task. This difficulty stems from the complex relationship between the threat levels of enemy units and their feature characteristics, which complicates the design of rule-based evaluators. Moreover, traditional supervised learning methods face the challenge of lacking explicit labels during training when applied to this threat evaluation problem. In this study, we redefine the threat evaluation problem as a reinforcement learning task and introduce an efficient evaluator training algorithm, Eval-PPO, based on the Proximal Policy Optimization (PPO) algorithm. Eval-PPO integrates multidimensional enemy features and the state information of friendly units through systematic training, thereby achieving precise threat assessment. Compared with rule-based methods, Eval-PPO demonstrates a significant improvement in average success rate, with an increase of 17.84%.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Eval-PPO: Building an Efficient Threat Evaluator Using Proximal Policy Optimization
Sun, Wuzhou
Li, Siyi
Zou, Qingxiang
Liao, Zixing
Machine Learning
In various game scenarios, selecting a fixed number of targets from multiple enemy units is an extremely challenging task. This difficulty stems from the complex relationship between the threat levels of enemy units and their feature characteristics, which complicates the design of rule-based evaluators. Moreover, traditional supervised learning methods face the challenge of lacking explicit labels during training when applied to this threat evaluation problem. In this study, we redefine the threat evaluation problem as a reinforcement learning task and introduce an efficient evaluator training algorithm, Eval-PPO, based on the Proximal Policy Optimization (PPO) algorithm. Eval-PPO integrates multidimensional enemy features and the state information of friendly units through systematic training, thereby achieving precise threat assessment. Compared with rule-based methods, Eval-PPO demonstrates a significant improvement in average success rate, with an increase of 17.84%.
title Eval-PPO: Building an Efficient Threat Evaluator Using Proximal Policy Optimization
topic Machine Learning
url https://arxiv.org/abs/2503.12098