mlsanityData to 14 Oct 2026

Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability

arXiv 2607.18368 ↗First posted 20 Jul 2026cs.AIcited by 0

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 34 references that are in the map. First posted on arXiv 20 Jul 2026.

Builds on

18 of 34 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  5. 2014Neural Turing Machinescited by 644
  6. 2020Knowledge Graphscited by 621
  7. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  8. 2016The Option-Critic Architecturecited by 448
  9. 2018An Introduction to Deep Reinforcement Learningcited by 206
  10. 2017Neural Episodic Controlcited by 151
  11. 2020Complex Query Answering with Neural Link Predictorscited by 99
  12. 2017Neural Map: Structured Memory for Deep Reinforcement Learningcited by 90
6 more
  1. 2020Message Passing for Hyper-Relational Knowledge Graphscited by 79
  2. 2018Unsupervised Predictive Memory in a Goal-Directed Agentcited by 55
  3. 2021Query Embedding on Hyper-relational Knowledge Graphscited by 23
  4. 2017On overfitting and asymptotic bias in batch reinforcement learning with partial observabilitycited by 16
  5. 2018Towards Symbolic Reinforcement Learning with Common Sensecited by 12
  6. 2023Neuro-symbolic Meta Reinforcement Learning for Tradingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
  2. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
  3. 2026Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning
  4. 2026MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
  5. 2026Sample-Efficient Neurosymbolic Deep Reinforcement Learning
  6. 2026Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures
  7. 2026From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay
  8. 2026Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory