We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based algorithm and knowledge graph embedding methods on Freebase and Never-Ending Language Learning datasets.
@article{arxiv.1707.06690,
title = {DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning},
author = {Wenhan Xiong and Thien Hoang and William Yang Wang},
journal= {arXiv preprint arXiv:1707.06690},
year = {2018}
}