EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making
EvoCurr:面向复杂决策的、结合行为代码生成的自演进课程框架
机构 * Zhongguancun Academy(中关村学院) ; Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院) ; University of Science and Technology of China(中国科学技术大学) ; King Abdullah University of Science and Technology(国王 Abdullah 科学技术大学) ; Xi’an Jiaotong University(西安交通大学)
AI总结 提出EvoCurr这一推理时框架,协同演进课程与可执行策略,在《星际争霸II》等任务上实现高胜率,且具有通用性,无需训练LLM参数。