arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.02098cs.AI
收藏

具有短期、事件性和语义记忆系统的机器

A Machine with Short-Term, Episodic, and Semantic Memory Systems

Vrije Universiteit Amsterdam(瓦赫宁海姆大学);Technische Universiteit Delft(代尔夫特理工大学)

Taewoon Kim, Michael Cochez, Vincent François-Lavet, Mark Neerincx, Piek Vossen

AI总结:

本文提出了一种具有短期、事件性和语义记忆系统的智能体模型,通过知识图谱实现各记忆系统的建模,并在自研环境中验证了该模型在记忆编码、存储与检索上的优势。

摘要:

受人类显性记忆系统理论启发,本文构建了一个包含短期、事件性和语义记忆系统的智能体模型,每个记忆系统均用知识图谱建模。为评估该系统并分析智能体行为,我们设计并发布了自研强化学习环境

英文摘要:

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, "the Room", where an agent has to learn how to encode, store, and retrieve memories to maximize its return by answering questions. We show that our deep Q-learning based agent successfully learns whether a short-term memory should be forgotten, or rather be stored in the episodic or semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.

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。

↑