# XLVIN: eXecuted Latent Value Iteration Nets

arXiv: https://arxiv.org/abs/2010.13146 · HTML: https://mlsanity.com/paper/2010.13146/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 17 of 17)

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)
- [Backpropagation through Combinatorial Algorithms: Identity with Projection Works](https://mlsanity.com/paper/2205.15213/) (2022)
- [How to transfer algorithmic reasoning knowledge to learn new algorithms?](https://mlsanity.com/paper/2110.14056/) (2021)
- [Neural Algorithmic Reasoning for Combinatorial Optimisation](https://mlsanity.com/paper/2306.06064/) (2023)
- [Persistent Message Passing](https://mlsanity.com/paper/2103.01043/) (2021)
- [Reasoning-Modulated Representations](https://mlsanity.com/paper/2107.08881/) (2021)
- [Algorithmic Concept-based Explainable Reasoning](https://mlsanity.com/paper/2107.07493/) (2021)
- [Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing](https://mlsanity.com/paper/2103.01009/) (2021)
- [Learning Graph Search Heuristics](https://mlsanity.com/paper/2212.03978/) (2022)
- [Latent Space Representations of Neural Algorithmic Reasoners](https://mlsanity.com/paper/2307.08874/) (2023)
- [Myriad: a real-world testbed to bridge trajectory optimization and deep learning](https://mlsanity.com/paper/2202.10600/) (2022)
- [NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms](https://mlsanity.com/paper/2410.11031/) (2024)
- [Generalizable Reasoning through Compositional Energy Minimization](https://mlsanity.com/paper/2510.20607/) (2025)
- [UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG](https://mlsanity.com/paper/2603.28773/) (2026)
- [Convex Compositional Reasoning Models](https://mlsanity.com/paper/2605.23395/) (2026)

## Abstract (arXiv)

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics. This came with several limitations, however: the model is not incentivised in any way to perform meaningful planning computations, the underlying state space is assumed to be discrete, and the Markov decision process (MDP) is assumed fixed and known. We propose eXecuted Latent Value Iteration Networks (XLVINs), which combine recent developments across contrastive self-supervised learning, graph representation learning and neural algorithmic reasoning to alleviate all of the above limitations, successfully deploying VIN-style models on generic environments. XLVINs match the performance of VIN-like models when the underlying MDP is discrete, fixed and known, and provides significant improvements to model-free baselines across three general MDP setups.