# Representation Learning on Graphs: A Reinforcement Learning Application

arXiv: https://arxiv.org/abs/1901.05351 · HTML: https://mlsanity.com/paper/1901.05351/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2019.

## Built on by (most cited first, 5 of 5)

- [On the Generalization of Representations in Reinforcement Learning](https://mlsanity.com/paper/2203.00543/) (2022)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems](https://mlsanity.com/paper/2308.11336/) (2023)
- [Learn Dynamic-Aware State Embedding for Transfer Learning](https://mlsanity.com/paper/2101.02230/) (2021)
- [Self-supervised Learning for Heterogeneous Graph via Structure Information based on Metapath](https://mlsanity.com/paper/2209.04218/) (2022)

## Abstract (arXiv)

In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low dimensions and we highlight the importance of features learning for an improved low-dimensional value function approximation. Then, we adopt different representation learning algorithm on graphs to learn the basis functions that best represent the value function. We empirically show that node2vec, an algorithm for scalable feature learning in networks, and the Variational Graph Auto-Encoder constantly outperform the commonly used smooth proto-value functions in low-dimensional feature space.