Guardado en:
Detalles Bibliográficos
Autores principales: Li, Lingfeng, Lu, Yunlong, Wang, Yongyi, Li, Wenxin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.16995
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909799292076032
author Li, Lingfeng
Lu, Yunlong
Wang, Yongyi
Li, Wenxin
author_facet Li, Lingfeng
Lu, Yunlong
Wang, Yongyi
Li, Wenxin
contents Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency, whereas methods based on evolution algorithms generate agents with diverse play styles but exhibit subpar performance compared to RL methods. To address this gap, this paper proposes Mixed Proximal Policy Optimization (MPPO), a method designed to improve the proficiency of existing suboptimal agents while retaining their distinct styles. MPPO unifies loss objectives for both online and offline samples and introduces an implicit constraint to approximate demonstrator policies by adjusting the empirical distribution of samples. Empirical results across environments of varying scales demonstrate that MPPO achieves proficiency levels comparable to, or even superior to, pure online algorithms while preserving demonstrators' play styles. This work presents an effective approach for generating highly proficient and diverse game agents, ultimately contributing to more engaging gameplay experiences.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16995
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Style-Preserving Policy Optimization for Game Agents
Li, Lingfeng
Lu, Yunlong
Wang, Yongyi
Li, Wenxin
Artificial Intelligence
Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency, whereas methods based on evolution algorithms generate agents with diverse play styles but exhibit subpar performance compared to RL methods. To address this gap, this paper proposes Mixed Proximal Policy Optimization (MPPO), a method designed to improve the proficiency of existing suboptimal agents while retaining their distinct styles. MPPO unifies loss objectives for both online and offline samples and introduces an implicit constraint to approximate demonstrator policies by adjusting the empirical distribution of samples. Empirical results across environments of varying scales demonstrate that MPPO achieves proficiency levels comparable to, or even superior to, pure online algorithms while preserving demonstrators' play styles. This work presents an effective approach for generating highly proficient and diverse game agents, ultimately contributing to more engaging gameplay experiences.
title Style-Preserving Policy Optimization for Game Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2506.16995