Multi-Modal Deep Reinforcement Learning in ViZDoom with Audio Component.

Artem Sayapin Ilya Makarov

Published in: SISY (2022)

Keyphrases

multi modal
reinforcement learning
audio visual
cross modal
single modality
multi modality
multimedia
fusing multiple
state space
semantic concepts
visual information
video search
machine learning
high dimensional
audio features
computer vision
learning algorithm