计算机科学
人工智能
人工生命
学习规律
强化学习
基于规则的系统
生成语法
集合(抽象数据类型)
机器学习
适应(眼睛)
人工神经网络
光学
物理
程序设计语言
作者
Jiyao Pu,Haoran Duan,Junzhe Zhao,Yang Long
标识
DOI:10.1109/tcsvt.2023.3334526
摘要
The evolution of natural life is guided by a perpetually adaptive set of rules, encompassing natural laws, human policies, and game mechanics. Automated game design, through the creation of simulated environments populated by AI agents, embodies these rules, aligning with the objectives of artificial life research that seeks to replicate the dynamics of biological life through computational models. This paper presents a comprehensive framework, the Rule Generation Networks (RGN), devised for automated rule design, evaluation, and evolution in line with controllable expectations. We refine and formalize three cardinal elements - rules, strategies, and evaluation - to elucidate the intricate relationships inherent in rule generation tasks. The RGN integrates generative neural networks for rule design and a suite of reinforcement learning models for rule evaluation. To exemplify rule evolution and adaptation across varying environments, we introduce a controllability metric to gauge game dynamics and evolve the rule designer accordingly. Furthermore, we develop two game environments, Maze Run and Trust Evolution, modelling human exploration and societal trade dynamics, to gamify and evaluate the generated rules.
科研通智能强力驱动
Strongly Powered by AbleSci AI