MazeExplorer: A Customisable 3D Benchmark for Assessing Generalisation in Reinforcement Learning

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.