Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning - Archive ouverte HAL Access content directly
Conference Papers Year :

Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning

Abstract

Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents. It is of lower complexity compared to similar 3D platforms (e.g. Deep-Mind Lab or VizDoom), but emulates physical properties of the real world, such as continuity, multi-modal partially-observable states with first-person view and coherent physics. We propose to use it as an intermediary benchmark for problems related to Lifelong Learning. Flatland is highly customizable and offers a wide range of task difficulty to extensively evaluate the properties of artificial agents. We experiment with three reinforcement learning baseline agents and show that they can rapidly solve a navigation task in Flatland. A video of an agent acting in Flatland is available here: https://youtu.be/I5y6Y2ZypdA.
Fichier principal
Vignette du fichier
1809.00510 (1).pdf (409.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01951945 , version 1 (11-12-2018)

Identifiers

  • HAL Id : hal-01951945 , version 1

Cite

Hugo Caselles-Dupré, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz, David Filliat. Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning. Workshop on Continual Unsupervised Sensorimotor Learning, ICDL-EpiRob 2018, Sep 2018, Tokyo, Japan. ⟨hal-01951945⟩
73 View
221 Download

Share

Gmail Facebook Twitter LinkedIn More