Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment

2024-06-03 · Chen Zhang, Qiang He, Zhou Yuan, Elvis S. Liu, Hong Wang, Jian Zhao, Yang Wang

Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agent system for fighting games named Sh\=ukai, which has been successfully deployed to Naruto Mobile, a popular fighting game with over 100 million registered users. Sh\=ukai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency. Furthermore, Sh\=ukai implements specific rewards to align the agent's behavior with human expectations. Sh\=ukai's ability to generalize is demonstrated by its consistent competence across all characters, even though it was trained on only 13% of them. Additionally, HELT exhibits a remarkable 22% improvement in sample efficiency. Sh\=ukai serves as a valuable training partner for players in Naruto Mobile, enabling them to enhance their abilities and skills.

📄 PDF Abstract BibTeX arXiv:2406.01103

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

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

2019-04-08 · Inseok Oh, Seungeun Rho, Sangbin Moon, Seongho Son 외

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 boar…

Board Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Deep Reinforcement Learning for Playing 2.5D Fighting Games

2018-05-05 · Yu-Jhe Li, Hsin-Yu Chang, Yu-Jing Lin, Po-Wei Wu 외

Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreove…

Deep Reinforcement Learning OpenAI Gym reinforcement-learning Reinforcement Learning+1

Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI

2022-11-04 · Emily Halina, Matthew Guzdial

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strat…

Deep Reinforcement Learning Diversity reinforcement-learning Reinforcement Learning (RL)

Introduction to Behavior Algorithms for Fighting Games

2020-07-06 · Ignacio Gajardo, Felipe Besoain, Nicolas A. Barriga

The quality of opponent Artificial Intelligence (AI) in fighting videogames is crucial. Some other game genres can rely on their story or visuals, but fighting games are all about the adversarial experience. In this pape…

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

2025-04-10 · Shouren Wang, Zehua Jiang, Fernando Sliva, Sam Earle 외

Deep reinforcement learning (DRL) has effectively enhanced gameplay experiences and game design across various game genres. However, few studies on fighting game agents have focused explicitly on enhancing player enjoyme…

Deep Reinforcement Learning Game Design Large Language Model