A survey on intrinsic motivation in reinforcement learning

A Aubret, L Matignon, S Hassas - arXiv preprint arXiv:1908.06976, 2019 - arxiv.org
The reinforcement learning (RL) research area is very active, with an important number of
new contributions; especially considering the emergent field of deep RL (DRL). However a …

Learning abstract representations through lossy compression of multimodal signals

C Wilmot, G Baldassarre… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
A key competence for open-ended learning is the formation of increasingly abstract
representations useful for driving complex behavior. Abstract representations ignore specific …

Learning torsional eye movements through active efficient coding

Q Zhu, C Zhang, J Triesch, BE Shi - … Computing and Engineering, 2022 - iopscience.iop.org
The human eye has three rotational degrees of freedom: azimuthal, elevational, and
torsional. Although torsional eye movements have the most limited excursion, Hering and …

A neural model of binocular saccade planning and vergence control

W Muhammad, MW Spratling - Adaptive Behavior, 2015 - journals.sagepub.com
The human visual system uses saccadic and vergence eye movements to foveate visual
targets. To mimic this aspect of the biological visual system the PC/BC-DIM neural network is …

[HTML][HTML] Joint learning of binocularly driven saccades and vergence by active efficient coding

Q Zhu, J Triesch, BE Shi - Frontiers in neurorobotics, 2017 - frontiersin.org
This paper investigates two types of eye movements: vergence and saccades. Vergence eye
movements are responsible for bringing the images of the two eyes into correspondence …

Self-calibrating active binocular vision via active efficient coding with deep autoencoders

C Wilmot, BE Shi, J Triesch - 2020 Joint IEEE 10th International …, 2020 - ieeexplore.ieee.org
We present a model of the self-calibration of active binocular vision comprising the
simultaneous learning of visual representations, vergence, and pursuit eye movements. The …

Autonomous, self-calibrating binocular vision based on learned attention and active efficient coding

Q Zhu, J Triesch, BE Shi - 2017 Joint IEEE International …, 2017 - ieeexplore.ieee.org
We present a self-calibrating binocular vision system that autonomously learns how to
encode the visual input and how to move its eyes. The model combines the learning of …

Learning of active binocular vision in a biomechanical model of the oculomotor system

L Klimmasch, A Lelais, A Lichtenstein… - 2017 Joint IEEE …, 2017 - ieeexplore.ieee.org
We present a model for the autonomous learning of active binocular vision using a recently
developed biomechanical model of the human oculomotor system. The model is formulated …

[HTML][HTML] An active-efficient-coding model of optokinetic nystagmus

C Zhang, J Triesch, BE Shi - Journal of vision, 2016 - iovs.arvojournals.org
Optokinetic nystagmus (OKN) is an involuntary eye movement responsible for stabilizing
retinal images in the presence of relative motion between an observer and the environment …

A self-trainable depth perception method from eye pursuit and motion parallax

T Prucksakorn, S Jeong, NY Chong - Robotics and Autonomous Systems, 2018 - Elsevier
When humans move in a lateral direction (frontal plane), they intuitively understand the
motion parallax phenomenon while jointly developing sensory neurons and pursuit eye …