# Generalized Value Iteration Networks: Life Beyond Lattices

arXiv: https://arxiv.org/abs/1706.02416 · HTML: https://mlsanity.com/paper/1706.02416/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2017.

## Built on by (most cited first, 16 of 16)

- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Neural Algorithmic Reasoners are Implicit Planners](https://mlsanity.com/paper/2110.05442/) (2021)
- [Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks](https://mlsanity.com/paper/2210.08864/) (2022)
- [Hierarchies of Planning and Reinforcement Learning for Robot Navigation](https://mlsanity.com/paper/2109.11178/) (2021)
- [Accelerating Value Iteration with Anchoring](https://mlsanity.com/paper/2305.16569/) (2023)
- [Integrating Symmetry into Differentiable Planning with Steerable Convolutions](https://mlsanity.com/paper/2206.03674/) (2022)
- [Neural Message Passing for Visual Relationship Detection](https://mlsanity.com/paper/2208.04165/) (2022)
- [Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation](https://mlsanity.com/paper/2210.13542/) (2022)
- [E(2)-Equivariant Graph Planning for Navigation](https://mlsanity.com/paper/2309.13043/) (2023)
- [Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding](https://mlsanity.com/paper/2210.08408/) (2022)
- [Continuous Neural Algorithmic Planners](https://mlsanity.com/paper/2211.15839/) (2022)
- [Reward Shaping Using Convolutional Neural Network](https://mlsanity.com/paper/2210.16956/) (2022)
- [Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning](https://mlsanity.com/paper/2406.08404/) (2024)
- [Path Planning using Reinforcement Learning: A Policy Iteration Approach](https://mlsanity.com/paper/2303.07535/) (2023)
- [Fast End-to-End Generation of Belief Space Paths for Minimum Sensing Navigation](https://mlsanity.com/paper/2409.12902/) (2024)
- [Unrolling Dynamic Programming via Graph Filters](https://mlsanity.com/paper/2507.21705/) (2025)

## Abstract (arXiv)

In this paper, we introduce a generalized value iteration network (GVIN), which is an end-to-end neural network planning module. GVIN emulates the value iteration algorithm by using a novel graph convolution operator, which enables GVIN to learn and plan on irregular spatial graphs. We propose three novel differentiable kernels as graph convolution operators and show that the embedding based kernel achieves the best performance. We further propose episodic Q-learning, an improvement upon traditional n-step Q-learning that stabilizes training for networks that contain a planning module. Lastly, we evaluate GVIN on planning problems in 2D mazes, irregular graphs, and real-world street networks, showing that GVIN generalizes well for both arbitrary graphs and unseen graphs of larger scale and outperforms a naive generalization of VIN (discretizing a spatial graph into a 2D image).