… a novel neural network-based reinforcement learning approach for robot gaze control. Our
… In this paper, we presented a neural network-based reinforcement learning approach to …

… audio-visual gaze control in the specific context of human-robot interaction, namely how
controlled robot … LSTM (a recurrent neural network model) that allow us to experiment with early …

… such as human walking trajectory, face expression, gaze direction, … in machine learning
has combined deep learning with … DQN utilizes deep convolutional neural network [5] for the …

… (a neural network recurrent model)-based deep networks we … visual information. The
action-value function is described by … Robot behavior adaptation for humanrobot interaction based …

… , robotics, to name a few. Most importantly, DRL algorithms are also being employed in …
Deep neural networks (DNNs) have been shown to produce state-of-the-art results in audio and …

… gaze behavior. A comparison of the human gaze behavior with the behavior of our gaze-control
system running on the same videos shows that it replicated human gaze behavior 89% …

… and simpler learning approaches. Third, We propose a … reinforcement learning method for
robotic gaze control. The model is based on a recurrent neural network architecture to learn a …

… hand-crafting robot behavior, we explore the use of machine learning for robot autonomy in
Human-Robot Interaction (… Horaud, “Neural network based reinforcement learning for audio–…

… introduces a novel neural network-based reinforcement learning approach for robot gaze
control. Our approach enables a robot to learn and adapt its gaze control strategy for human-…

… -end network that consists of audiovisual CA, BLF, and SA to … In this work, they also explored
gaze as the only feature and … tional neural network [19] to detect the addressee from visual …