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

arXiv:2607.18368 · cs.AI · Submitted 2026-07-20 · Read on arXiv

cs.AI

Submitted: 2026-07-20

Updated: 2026-10-03

Comments: Accepted at ISWC 2026 (Research Track), to appear in LNCS 17126. v4: corrects author names in two references, an editor name, affiliation details, and a section cross-reference

Code: https://github.com/humemai/roomkg-meta-policies

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Resource Description Framework — 1× in this paper

Sources

• Towards Symbolic Reinforcement Learning with Common Sense
• Neuro-symbolic Meta Reinforcement Learning for Trading
• Deep Recurrent Q-Learning for Partially Observable MDPs
• Temporal Knowledge-Graph Memory in a Partially Observable Environment
• Unsupervised Predictive Memory in a Goal-Directed Agent

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems