arXiv 2108.035992021-08-08cs.AI

Identification of Play Styles in Universal Fighting Engine

The University of Aizu（会津大学）

Kaori Yuda, Shota Kamei, Riku Tanji, Ryoya Ito, Ippo Wakana, Maxim Mozgovoy

英文摘要：

AI-controlled characters in fighting games are expected to possess reasonably high skills and behave in a believable, human-like manner, exhibiting a diversity of play styles and strategies. Thus, the development of fighting game AI requires the ability to evaluate these properties. For instance, it should be possible to ensure that the characters created are believable and diverse. In this paper, we show how an automated procedure can be used to compare play styles of individual AI- and human-controlled characters, and to assess human-likeness and diversity of game participants.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

MAAIP：面向基于物理的角色格斗演示模仿的多智能体对抗交互先验

MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters

Inria（法国国家信息与自动化研究所）；IRISA（法国信息与自动化研究实验室）；University of Rennes（雷恩大学）；University Rennes 2（雷恩第二大学）；M2S（运动、运动学与健康实验室）

针对多角色交互模仿难题，提出基于多智能体生成对抗模仿学习的MAAIP方法，利用单角色与少量交互数据集训练策略，实现保留风格的多角色格斗交互模仿，在两种格斗风格上验证了有效性。

2023-11-04cs.AIcs.CVcs.GR

Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning

NCSOFT（NCsoft公司）

Reinforcement learning combined with deep neural networks has performed remarkably well in many genres of games recently. It has surpassed human-level performance in fixed game environments and turn-based two player board games. However, to the best of our knowledge, current research has yet to produce a result that has surpassed human-level performance in modern complex fighting games. This is due to the inherent difficulties with real-time fighting games, including: vast action spaces, action dependencies, and imperfect information. We overcame these challenges and made 1v1 battle AI agents …

2020-01-31cs.AIcs.LG

基于双层DRL与LLM智能体系统提升格斗游戏玩家乐趣

Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games

New York University（纽约大学）；Case Western Reserve University（凯斯西储大学）

本文提出双层智能体系统，结合DRL与LLM超智能体，在《街头霸王 II》中动态选择对手以提升玩家乐趣，实验显示高级技能执行率提升64.36%至156.36%，用户研究验证了系统有效性。

2025-04-10cs.AIcs.LG

Enhanced Rolling Horizon Evolution Algorithm with Opponent Model Learning: Results for the Fighting Game AI Competition

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Queen Mary University of London（伦敦玛丽女王大学）

The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this paper, we propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient …

2020-03-31cs.AIcs.LG

深度风格匹配互补推荐

Deep Style Match for Complementary Recommendation

College of Computer Science, Zhejiang University（浙江大学计算机科学与技术学院）；Hangzhou Science & Technology Information Research Institute（杭州市科技信息研究院）

人类根据物品的属性发展出一种共同的风格兼容性。我们试图自动回答这样的问题：“这件衬衫和那条牛仔裤配吗？为了回答这类问题，我们试图在本文中建立人类风格兼容性的模型。我们的方法的基本假设是，在线商店中产品的大多数重要属性都包含在其标题描述中。因此，从这些描述中学习风格兼容性是可行的。我们设计了一个连体卷积神经网络架构，并提供它与标题对的项目，这是兼容或不兼容。这些对将从符号词的原始空间映射到一些嵌入的样式空间。我们的方法只需要单词作为输入，预处理很少，没有费力和昂贵的特征工程。

2017-08-26cs.AI

Elo-解缠的棋手风格嵌入：基于等级条件残差走棋模型的人类国际象棋

Matilda: Engine-Agnostic Search with Human Policy Guidance

提出一种残差公式，通过等级条件基础模型和冻结副本，学习与棋力（Elo）近似解缠的棋手风格嵌入，实现风格相似性度量与棋力分离。

2026-07-30cs.AI

更多相关论文收起更多论文

当内容是歌利亚而算法是大卫：生成式搜索引擎的风格与语义效应

When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine

Belk College of Business, University of North Carolina at Charlotte（北卡罗来纳州立大学查尔斯顿分校商学院）；Faculty of Business for Science and Technology, School of Management, University of Science and Technology of China（中国科学技术大学管理学院科学技术商学院）；Michael G. Foster School of Business, University of Washington（华盛顿大学Michael G. Foster商学院）

本文通过构建约一万个网站的数据集和受控实验，揭示生成式搜索引擎偏好引用对LLM可预测性高且语义相似的内容，并发现LLM内容润色能增强AI摘要信息多样性、对不同教育程度用户产生差异化影响。

2025-09-17cs.AIcs.IR

从比赛记录中学习球员风格的方法

A Methodology for Learning Players' Styles from Game Records

Birkbeck College, University of London（伦敦大学伯贝克学院）

我们描述了一个初步的调查学习国际象棋选手的风格，从游戏记录。该方法是基于尝试学习的球员的个人评价功能的时间差异的方法，与传统的国际象棋引擎架构的帮助下。一些令人鼓舞的结果是在学习风格的两个最近的国际象棋世界冠军，我们报告我们试图使用学到的风格来区分球员之间的游戏记录，试图检测谁是白色的，谁是黑色的。我们还讨论了我们的方法的一些局限性，并提出了未来研究的可能方向。我们提出的方法也可以适用于其他战略游戏，甚至可以推广到其他领域的代理人的行动序列记录。

2009-04-16cs.AIcs.LG

几次引擎走棋能有多大帮助？量化国际象棋中的有限作弊

How Much Can a Few Engine Moves Help? Quantifying Limited Cheating in Chess

Department of Computer Science（计算机科学系）；University of Haifa（海法大学）；Haifa, Israel（以色列海法）

本文通过阈值策略和Bellman策略，在Stockfish引擎对弈中量化有限次作弊对棋手得分的影响，并引入无引擎模拟器优化超参数。

2026-05-26cs.AI

迈向全息甲板风格的模拟游戏

Towards a Holodeck-style Simulation Game

Webaverse

Infinitia 是一款利用生成式模型根据玩家描述动态重塑设定和 NPC 的模拟游戏系统，提供无限世界、行为可控、多人协作等功能，采用 Unity 引擎和服务器-客户端架构，支持社区扩展。

2023-09-12cs.AI

Cine-AI: Generating Video Game Cutscenes in the Style of Human Directors

Aalto University（阿尔托大学）

Cutscenes form an integral part of many video games, but their creation is costly, time-consuming, and requires skills that many game developers lack. While AI has been leveraged to semi-automate cutscene production, the results typically lack the internal consistency and uniformity in style that is characteristic of professional human directors. We overcome this shortcoming with Cine-AI, an open-source procedural cinematography toolset capable of generating in-game cutscenes in the style of eminent human directors. Implemented in the popular game engine Unity, Cine-AI features a novel timelin…

2022-08-11cs.AIcs.HCcs.MM

GhostWriter：通过个性化与自主性增强人机协作写作体验

GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency

Harvard University（哈佛大学）；Microsoft Research（微软研究院）；Microsoft（微软）

GhostWriter通过隐式学习用户写作风格并提供显式风格优化与反思机制，在AI辅助写作中增强用户个性化与控制力，基于18人用户研究验证其有效性并提出设计建议。

2025-07-04cs.AIcs.HC

基于角色的服装生成：通过 LLMs 进行视觉增强的风格提取

Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs

Walmart Global Tech（沃尔玛全球科技）

本文提出了基于角色的服装生成（COG）问题及框架 LVA-COG，利用 LLMs 提取角色兴趣并采用提示工程理解偏好，结合文本到图像模型增强视觉理解与生成，实现个性化服装推荐。

2024-02-02cs.AIcs.CVcs.IR

使用 Delta-Engine 的开放式角色扮演

Open Role-Playing with Delta-Engines

Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）

本文提出开放式角色扮演游戏（ORPG）和 Delta-Engine，通过基础引擎与 LLM 神经代理增量生成代码，让玩家用自然语言自由塑造角色成长，并以改编自《宝可梦》的自研游戏验证其数据生成与引擎性能。

2025-03-07cs.AIcs.HC

Understanding why shooters shoot -- An AI-powered engine for basketball performance profiling

UC San Diego（加州大学圣迭戈分校）

Understanding player shooting profiles is an essential part of basketball analysis: knowing where certain opposing players like to shoot from can help coaches neutralize offensive gameplans from their opponents; understanding where their players are most comfortable can lead them to developing more effective offensive strategies. An automatic tool that can provide these performance profiles in a timely manner can become invaluable for coaches to maximize both the effectiveness of their game plan as well as the time dedicated to practice and other related activities. Additionally, basketball is…

2023-03-17cs.AIcs.LG