# Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer

arXiv: https://arxiv.org/abs/1904.01806 · HTML: https://mlsanity.com/paper/1904.01806/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [Multi-Object Navigation with dynamically learned neural implicit representations](https://mlsanity.com/paper/2210.05129/) (2022)
- [Megaverse: Simulating Embodied Agents at One Million Experiences per Second](https://mlsanity.com/paper/2107.08170/) (2021)
- [Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation](https://mlsanity.com/paper/2107.06011/) (2021)
- [Recurrent Action Transformer with Memory](https://mlsanity.com/paper/2306.09459/) (2023)
- [Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation](https://mlsanity.com/paper/2307.06125/) (2023)
- [Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes](https://mlsanity.com/paper/2207.13649/) (2022)
- [An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments](https://mlsanity.com/paper/2111.14666/) (2021)
- [Multi-Object Navigation in real environments using hybrid policies](https://mlsanity.com/paper/2401.13800/) (2024)
- [Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' Labyrinth](https://mlsanity.com/paper/2404.06529/) (2024)
- [Do We Need Transformers to Play FPS Video Games?](https://mlsanity.com/paper/2504.17891/) (2025)

## Abstract (arXiv)

An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When trained from simulations, optimal environments should satisfy a currently unobtainable combination of high-fidelity photographic observations, massive amounts of different environment configurations and fast simulation speeds. In this paper we argue that research on training agents capable of complex reasoning can be simplified by decoupling from the requirement of high fidelity photographic observations. We present a suite of tasks requiring complex reasoning and exploration in continuous, partially observable 3D environments. The objective is to provide challenging scenarios and a robust baseline agent architecture that can be trained on mid-range consumer hardware in under 24h. Our scenarios combine two key advantages: (i) they are based on a simple but highly efficient 3D environment (ViZDoom) which allows high speed simulation (12000fps); (ii) the scenarios provide the user with a range of difficulty settings, in order to identify the limitations of current state of the art algorithms and network architectures. We aim to increase accessibility to the field of Deep-RL by providing baselines for challenging scenarios where new ideas can be iterated on quickly. We argue that the community should be able to address challenging problems in reasoning of mobile agents without the need for a large compute infrastructure.