# Graph neural induction of value iteration

arXiv: https://arxiv.org/abs/2009.12604 · HTML: https://mlsanity.com/paper/2009.12604/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [The CLRS Algorithmic Reasoning Benchmark](https://mlsanity.com/paper/2205.15659/) (2022)
- [Neural Algorithmic Reasoners are Implicit Planners](https://mlsanity.com/paper/2110.05442/) (2021)
- [Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective](https://mlsanity.com/paper/2404.06492/) (2024)
- [Convergent Graph Solvers](https://mlsanity.com/paper/2106.01680/) (2021)
- [Primal-Dual Neural Algorithmic Reasoning](https://mlsanity.com/paper/2505.24067/) (2025)
- [Future Directions in the Theory of Graph Machine Learning](https://mlsanity.com/paper/2402.02287/) (2024)
- [Continuous Neural Algorithmic Planners](https://mlsanity.com/paper/2211.15839/) (2022)
- [Unrolling Dynamic Programming via Graph Filters](https://mlsanity.com/paper/2507.21705/) (2025)

## Abstract (arXiv)

Many reinforcement learning tasks can benefit from explicit planning based on an internal model of the environment. Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration. Such network have so far been focused on restrictive environments (e.g. grid-worlds), and modelled the planning procedure only indirectly. We relax these constraints, proposing a graph neural network (GNN) that executes the value iteration (VI) algorithm, across arbitrary environment models, with direct supervision on the intermediate steps of VI. The results indicate that GNNs are able to model value iteration accurately, recovering favourable metrics and policies across a variety of out-of-distribution tests. This suggests that GNN executors with strong supervision are a viable component within deep reinforcement learning systems.