# Value Propagation Networks

arXiv: https://arxiv.org/abs/1805.11199 · HTML: https://mlsanity.com/paper/1805.11199/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 7 of 7)

- [Differentiable Spatial Planning using Transformers](https://mlsanity.com/paper/2112.01010/) (2021)
- [A Survey on Deep Reinforcement Learning for Audio-Based Applications](https://mlsanity.com/paper/2101.00240/) (2021)
- [High-Accuracy Model-Based Reinforcement Learning, a Survey](https://mlsanity.com/paper/2107.08241/) (2021)
- [Hierarchies of Planning and Reinforcement Learning for Robot Navigation](https://mlsanity.com/paper/2109.11178/) (2021)
- [Motion Planning Transformers: A Motion Planning Framework for Mobile Robots](https://mlsanity.com/paper/2106.02791/) (2021)
- [Compositional Generalization in Grounded Language Learning via Induced Model Sparsity](https://mlsanity.com/paper/2207.02518/) (2022)
- [Value Iteration Networks with Gated Summarization Module](https://mlsanity.com/paper/2305.07039/) (2023)

## Abstract (arXiv)

We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement learning to solve unseen tasks, has the capability to generalize to larger map sizes, and can learn to navigate in dynamic environments. We show that the modules enable learning to plan when the environment also includes stochastic elements, providing a cost-efficient learning system to build low-level size-invariant planners for a variety of interactive navigation problems. We evaluate on static and dynamic configurations of MazeBase grid-worlds, with randomly generated environments of several different sizes, and on a StarCraft navigation scenario, with more complex dynamics, and pixels as input.