Exploring Deep Recurrent Q-Learning for Navigation in a 3D Environment
Journal Title: EAI Endorsed Transactions on Creative Technologies - Year 2018, Vol 5, Issue 14
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.
Authors and Affiliations
Rasmus Kongsmar Brejl, Henrik Purwins, Henrik Schoenau-Fog
Keywords
Related Articles
- EP ID EP45886
- DOI http://dx.doi.org/10.4108/eai.16-1-2018.153641
- Views 295
- Downloads 0
Dynamic Resource Allocation Scheme Using Cooperative Game for Multimedia Services in LTE Advanced System
In LTE Advanced system, it is critical to carry on various types of services for different user applications. Obviously, the system resource requirements are quite different for each individual service. In order to alloc...
Improvement of natural image search engines results by emotional filtering
With the Internet 2.0 era, managing user emotions is a problem that more and more actors are interested in. Historically, the first notions of emotion sharing were expressed and defined with emoticons. They allowed users...
A conceptual framework for audio-visual museum media
In today's history museums, the past is communicated through many other means than original artefacts. This interdisciplinary and theoretical article suggests a new approach to studying the use of audio-visual media, suc...
Evaluating Moodle use via Smart Mobile Phones. A case study in a Greek University
The use of learning management systems (LMS) has grown considerably in universities around the world. LMSs can offer a great variety of channels and workspaces to facilitate information sharing and communication among pa...
Designing intelligent games adapting to children’s playing maturity
Play is a voluntary activity in which individuals involve for pleasure. It is very important for children because through playing they learn to explore, develop and master physical and social skills. Play development is...