MazeExplorer: A Customisable 3D Benchmark for Assessing Generalisation in Reinforcement Learning
- Luke Harries ,
- Sebastian Lee ,
- Jaroslaw Rzepecki ,
- Katja Hofmann ,
- Sam Devlin
IEEE Conference on Games |
This paper presents a customisable 3D benchmark for assessing generalisability of reinforcement learning agents based on the 3D first-person game Doom and open source environment VizDoom. As a sample use-case we show that different domain randomisation techniques during training in a key-collection navigation task can help to improve agent performance on unseen evaluation maps.
Publication Downloads
MazeExplorer [1.0.0]
June 12, 2019
MazeExplorer is a customisable 3D benchmark for assessing generalisation in Reinforcement Learning. It is based on the 3D first-person game Doom and the open-source environment VizDoom. This repository contains the code for the MazeExplorer Gym Environment along with the scripts to generate baseline results.