Skip to Main content Skip to Navigation
Conference papers

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

Abstract : 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 (ViZ-Doom) 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 ar-chitectures. 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. Code for the generation of scenarios and training of baselines is available online at the following repository 1 .
Document type :
Conference papers
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download
Contributor : Edward Beeching <>
Submitted on : Wednesday, September 9, 2020 - 8:52:17 AM
Last modification on : Thursday, November 26, 2020 - 1:52:56 PM


Files produced by the author(s)


  • HAL Id : hal-02934130, version 1



Edward Beeching, Christian Wolf, Jilles Dibangoye, Olivier Simonin. Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer. ICPR 2020 - 25th International Conference on Pattern Recognition, Dec 2020, Milan, Italy. pp.1-16. ⟨hal-02934130⟩



Record views


Files downloads