# Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps

arXiv: https://arxiv.org/abs/2412.12024 · HTML: https://mlsanity.com/paper/2412.12024/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 45 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 30 of 35)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [Cognitive Mapping and Planning for Visual Navigation](https://mlsanity.com/paper/1702.03920/) (2017)
- [Learning to Navigate in Complex Environments](https://mlsanity.com/paper/1611.03673/) (2016)
- [Learning Continuous Control Policies by Stochastic Value Gradients](https://mlsanity.com/paper/1510.09142/) (2015)
- [Benchmarking Model-Based Reinforcement Learning](https://mlsanity.com/paper/1907.02057/) (2019)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [Value Prediction Network](https://mlsanity.com/paper/1707.03497/) (2017)
- [Learning Exploration Policies for Navigation](https://mlsanity.com/paper/1903.01959/) (2019)
- [Learning to Navigate in Cities Without a Map](https://mlsanity.com/paper/1804.00168/) (2018)
- [Playing FPS Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05521/) (2016)
- [Neural Map: Structured Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/1702.08360/) (2017)
- [Temporal Difference Models: Model-Free Deep RL for Model-Based Control](https://mlsanity.com/paper/1802.09081/) (2018)
- [DeepMind Lab](https://mlsanity.com/paper/1612.03801/) (2016)
- [Unsupervised Predictive Memory in a Goal-Directed Agent](https://mlsanity.com/paper/1803.10760/) (2018)
- [Mapping State Space using Landmarks for Universal Goal Reaching](https://mlsanity.com/paper/1908.05451/) (2019)
- [Continual Model-Based Reinforcement Learning with Hypernetworks](https://mlsanity.com/paper/2009.11997/) (2020)
- [ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero](https://mlsanity.com/paper/1902.04522/) (2019)
- [Learning to Act by Predicting the Future](https://mlsanity.com/paper/1611.01779/) (2016)
- [Generalization of Reinforcement Learners with Working and Episodic Memory](https://mlsanity.com/paper/1910.13406/) (2019)
- [Gated Path Planning Networks](https://mlsanity.com/paper/1806.06408/) (2018)

## Built on by (most cited first, 2 of 2)

- [NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps](https://mlsanity.com/paper/2605.06317/) (2026)
- [Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2608.02993/) (2026)

## Abstract (arXiv)

Learning navigation capabilities in different environments has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability using given abstract 2-D top-down maps. Like human navigation by reading a paper map, the agent reads the map as an image when navigating in a novel layout, after learning to navigate on a set of training maps. We propose a model-based reinforcement learning approach for this multi-task learning problem, where it jointly learns a hypermodel that takes top-down maps as input and predicts the weights of the transition network. We use the DeepMind Lab environment and customize layouts using generated maps. Our method can adapt better to novel environments in zero-shot and is more robust to noise.