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 287
- Downloads 0
Learnings from an Iterative Design Process for Technology-Mediated Audience Participation (TMAP) using Smartphones
We discuss a setup for technology-mediated audience participation (TMAP)in live music using smartphones and high-frequency sound IDs in a playful setting. The audience needs to install a smartphone app. Using high-freque...
A High Visual Quality Embedding Method in Edges Based on Pixel Pair Difference
In this paper, we proposed a new data hiding method based on diamond encoding (DE) and pixel pair difference (PPD). DE proposes a pixel-wise algorithm which flexibly embeds different base digits to maximize payload and i...
Towards a 15.5W Si-LDMOS Energy Efficient Balanced RF Power Amplifier for 5G-LTE Multi-carrier Applications
In this paper, a 15.5W Si-LDMOS balanced RF power amplifier has been designed using 2.620-2.690GHz frequency band to improve efficiency and linearity for 5G-LTE mobile applications. The amplifier was designed and simulat...
Solitude or co-existence – or learning-together-apart with digital dialogic technologies for kids with developmental and attention difficulties
An overall political vision of a prosperous society is one in which everyone has the same access and possibilities of participating in democratic processes, and in which everyone has equal access to the resources, life a...
Auditory and Visual based Intelligent Lighting Design for Music Concerts
Playing music is about conveying emotions and the lighting at a concert can help do that. However, without a dedicated light technician, many bands have to miss out on lighting that will help them to convey the emotions...