arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04663cs.NE
收藏

LLM-POET:利用大型语言模型演化复杂环境

LLM-POET: Evolving Complex Environments using Large Language Models

Fuma Aki, Riku Ikeda, Takumi Saito, Ciaran Regan, Mizuki Oka

AI总结:

本文提出LLM-POET算法,用大型语言模型替代CPPN来创建和变异演化环境,使共同演化性能增益提升34%,从而让智能体在更复杂环境中习得更丰富的技能。

摘要:

在人工智能领域,创建能够在没有预定目标或限制的情况下生成几乎无限多样且新颖行为的系统是一项重大挑战。为此,研究者开发了多种开放式算法,能够持续生成新的多样化行为,例如用于环境与智能体行为共同演化的POET和Enhanced-POET算法。然而,现有方法的一个挑战在于它们难以持续生成复杂环境。在本工作中,我们提出LLM-POET,这是对POET算法的一种改进,其中环境的创建和变异均由大型语言模型(LLM)完成。通过使用Evolution Gym环境的文本表示以及描述这些环境的说明文字对LLM进行微调,我们能够利用自然语言生成复杂且多样化的环境。我们发现,LLM不仅能产生多样化的环境,而且与Enhanced-POET中用于环境生成的CPPN相比,LLM使共同演化的性能增益提高了34%。这一性能提升表明,智能体通过在更复杂的环境上训练,能够学习到更加多样化的技能。

英文摘要:

Creating systems capable of generating virtually infinite variations of complex and novel behaviour without predetermined goals or limits is a major challenge in the field of AI. This challenge has been addressed through the development of several open-ended algorithms that can continuously generate new and diverse behaviours, such as the POET and Enhanced-POET algorithms for co-evolving environments and agent behaviour. One of the challenges with existing methods however, is that they struggle to continuously generate complex environments. In this work, we propose LLM-POET, a modification of the POET algorithm where the environment is both created and mutated using a Large Language Model (LLM). By fine-tuning a LLM with text representations of Evolution Gym environments and captions that describe the environment, we were able to generate complex and diverse environments using natural language. We found that not only could the LLM produce a diverse range of environments, but compared to the CPPNs used in Enhanced-POET for environment generation, the LLM allowed for a 34% increase in the performance gain of co-evolution. This increased performance suggests that the agents were able to learn a more diverse set of skills by training on more complex environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑