Exploring Deep Recurrent Q-Learning for Navigation in a 3D Environment

Brejl, Rasmus Kongsmar and Purwins, Henrik and Schoenau-Fog, Henrik (2018) Exploring Deep Recurrent Q-Learning for Navigation in a 3D Environment. EAI Endorsed Transactions on Creative Technologies, 5 (14): 3. ISSN 2409-9708

[img]
Preview
Text (PDF)
eai.16-1-2018.153641.pdf - Published Version
Available under License Creative Commons Attribution No Derivatives.

Download (1MB) | Preview

Abstract

Learning to navigate in 3D environments from raw sensory input is an important step towards bridging the gap between human players and artificial intelligence in digital games. Recent advances in deep reinforcement learning have seen success in teaching agents to play Atari 2600 games from raw pixel information where the environment is always fully observable by the agent. This is not true for first-person 3D navigation tasks. Instead, the agent is limited by its field of view which limits its ability to make optimal decisions in the environment. This paper explores using a Deep Recurrent Q-Network implementation with a long short-term memory layer for dealing with such tasks by allowing an agent to process recent frames and gain a memory of the environment. An agent was trained in a 3D first-person labyrinth-like environment for 2 million frames. Informal observations indicate that the trained agent navigated in the right direction but was unable to find the target of the environment.

Item Type: Article
Uncontrolled Keywords: Reinforcement Learning, Deep Learning, Q-Learning, Deep Recurrent Q-Learning, Artificial Intelligence, Navigation, Game Intelligence
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor II.
Date Deposited: 08 Sep 2020 11:37
Last Modified: 08 Sep 2020 11:37
URI: https://eprints.eudl.eu/id/eprint/73

Actions (login required)

View Item View Item