# Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning

arXiv: https://arxiv.org/abs/2312.09906 · HTML: https://mlsanity.com/paper/2312.09906/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 9 of 9)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [Neural Map: Structured Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/1702.08360/) (2017)
- [Combining Vision, Machine Learning and Automatic Control to Play the Labyrinth Game](https://mlsanity.com/paper/1604.00975/) (2016)

## Built on by (most cited first, 8 of 8)

- [Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics](https://mlsanity.com/paper/2501.10100/) (2025)
- [Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight](https://mlsanity.com/paper/2501.14377/) (2025)
- [On Rollouts in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2501.16918/) (2025)
- [Accelerating Model-Based Reinforcement Learning with State-Space World Models](https://mlsanity.com/paper/2502.20168/) (2025)
- [Combining Automated Optimisation of Hyperparameters and Reward Shape](https://mlsanity.com/paper/2406.18293/) (2024)
- [Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotion](https://mlsanity.com/paper/2604.08780/) (2026)
- [Privileged observations enable rapid and reliable policy discovery directly in the physical world](https://mlsanity.com/paper/2512.08463/) (2025)
- [E2DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation](https://mlsanity.com/paper/2605.00159/) (2026)

## Abstract (arXiv)

Motivated by the challenge of achieving rapid learning in physical environments, this paper presents the development and training of a robotic system designed to navigate and solve a labyrinth game using model-based reinforcement learning techniques. The method involves extracting low-dimensional observations from camera images, along with a cropped and rectified image patch centered on the current position within the labyrinth, providing valuable information about the labyrinth layout. The learning of a control policy is performed purely on the physical system using model-based reinforcement learning, where the progress along the labyrinth's path serves as a reward signal. Additionally, we exploit the system's inherent symmetries to augment the training data. Consequently, our approach learns to successfully solve a popular real-world labyrinth game in record time, with only 5 hours of real-world training data.