Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability

TL;DR

This paper introduces a neuro-symbolic approach for memory management in reinforcement learning with partial observability, focusing on short-term-to-long-term transfer in knowledge graphs, leading to improved decision-making.

Contribution

It proposes a novel Q-learning based method for explicit short-term-to-long-term memory transfer in knowledge graphs, outperforming existing symbolic and neural baselines.

Findings

Learned transfer decisions outperform baselines on RoomKG benchmark.

A lightweight local transfer policy performs best across ablations.

The policy effectively retains navigation- and query-relevant facts.

Abstract

Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer process in a temporal knowledge-graph memory setting and cast it as a neuro-symbolic value-based decision problem: for each observed triple, the agent chooses whether to keep or drop it before long-term insertion. To handle variable-sized short-term buffers, we use a per-item Q-learning design with shared parameters and a practical temporal-difference update over matched items across consecutive steps. On the RoomKG benchmark at long-term memory capacity 128, learned transfer decisions outperform symbolic and neural baselines, including symbolic baselines with temporal annotations and history-based LSTM/Transformer baselines. Across transfer-policy ablations, a lightweight local short-term-only variant performs best, and step-level behavior shows that the policy keeps navigation- and query-relevant facts while discarding lower-value candidate facts, supporting explicit and interpretable memory decisions under memory constraints.