部分可观测性下用于时态知识图谱记忆的神经符号元策略
Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability
浏览论文内容
中文总结 AI 辅助
研究部分可观测性下的强化学习,提出神经符号元策略,结合知识图谱编码与值头,通过RDF表示等实现语义网基础,在特定设置下限定符感知的StarE - GNN配置性能最佳且有可追溯性。
中文摘要 AI 辅助
部分可观测强化学习需要决定随着时间推移保留、检索和遗忘什么。我们引入了一种神经符号元策略,它在保持执行符号化的同时,学习在每个决策点应用哪种符号记忆启发式方法。我们的设置在RoomKG中使用时态知识图谱记忆,其中隐藏状态和观测值表示为资源描述框架(RDF)图,并且记忆通过时态RDF三元组注释进行增强。该模型将记忆内容的知识图谱编码与用于问答、探索和遗忘的值头相结合,产生了一个既自适应又可检查的控制器。通过基于RDF的表示、注释兼容的图语义以及对显式记忆状态的基于图的符号操作,这项工作具有直接的语义网基础。在长期记忆容量为512的训练/测试房间划分上,限定符感知的StarE - GNN配置在比较的符号、神经和神经符号系统中实现了最佳的留出性能,同时保留了记忆管理决策的步骤级可追溯性。
英文摘要
Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic. Our setting uses temporal knowledge-graph memory in RoomKG, where hidden state and observations are represented as Resource Description Framework (RDF) graphs and memory is augmented with temporal RDF triple annotations. The model combines knowledge-graph encoding of memory contents with value heads for question answering, exploration, and forgetting, yielding a controller that is both adaptive and inspectable. This gives the work a direct Semantic Web grounding through RDF-based representation, annotation-compatible graph semantics, and graph-based symbolic operations over explicit memory state. On train/test room splits at long-term memory capacity of 512, the qualifier-aware StarE-GNN configuration achieves the best held-out performance among the compared symbolic, neural, and neuro-symbolic systems while preserving step-level traceability of memory-management decisions.
发表机构
- HumemAI(胡梅人工智能公司)
- Vrije Universiteit Amsterdam(阿姆斯特丹自由大学)
- ELLIS Institute Finland & Abo Akademi University(芬兰埃利斯研究所和图尔库大学)
机构由 AI 辅助整理,请以论文原文为准。