PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning 文章

ArXiv CS.AI2026-05-26NEWSen作者: In-Chang Baek, Sung-Hyun Kim, Sam Earle, Zehua Jiang, Jin-Ha Noh, Julian Togelius, Kyung-Joong Kim
大语言模型
查看原文 →
关系图谱

PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning · 相关技术

相关技术

ginODEPLALLMlanguage model远程代码执行（RCE）研究法辛烷值reward functionreinforcement learningprompt engineeringevaldivide-and-conquer partitioningTeraStanSSEReferring expression comprehension (REC)PromptParts-of-Speech (POS) tagsOWLOTAMECLMMlarge language modelsL-DriveHISForARGANNAgent