1
PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning
用大语言模型自动设计奖励函数，为程序化内容生成强化学习提供新范式，突破人工奖励建模瓶颈。
arXiv:2502.10906v2 Announce Type: replace Abstract: Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-speci…