arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.14855cs.AIcs.LO
收藏

通过基于模型的RL增强抽象与推理语料库中的类比推理

Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL

Gwangju Institute of Science and Technology(光州科学技术院)

Jihwan Lee, Woochang Sim, Sejin Kim, Sundong Kim

AI总结:

本文提出基于模型的强化学习方法,通过构建内部模型解决抽象与推理语料库(ARC)中的类比推理任务,实验证明其比无模型RL在学习和泛化上更具优势。

摘要:

本文证明基于模型的强化学习(model-based RL)是类比推理任务的合适方法。我们假设基于模型的RL能通过创建内部模型更高效地解决类比推理任务。为验证此点,我们在抽象与推理语料库(ARC)任务上比较了基于模型的RL方法DreamerV3与无模型RL方法Proximal Policy Optimization。结果表明,基于模型的RL不仅在从单个任务中学习和泛化方面优于无模型RL,还在跨相似任务的推理中展现出显著优势。

英文摘要:

This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks.

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。

↑