تقرير
Intrinsic Motivation and Episodic Memories for Robot Exploration of High-Dimensional Sensory Spaces
| العنوان: | Intrinsic Motivation and Episodic Memories for Robot Exploration of High-Dimensional Sensory Spaces |
|---|---|
| المؤلفون: | Schillaci, Guido, Villalpando, Antonio Pico, Hafner, Verena Vanessa, Hanappe, Peter, Colliaux, David, Wintz, Timothée |
| المصدر: | Adaptive behaviour 2020 |
| سنة النشر: | 2020 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Robotics |
| الوصف: | This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional features from images, and of online learning of shallow neural networks representing the inverse and forward kinematics of the system have been used. The artificial curiosity system assigns interest values to a set of pre-defined goals, and drives the exploration towards those that are expected to maximise the learning progress. We propose the integration of an episodic memory in intrinsic motivation systems to face catastrophic forgetting issues, typically experienced when performing online updates of artificial neural networks. Our results show that adopting an episodic memory system not only prevents the computational models from quickly forgetting knowledge that has been previously acquired, but also provides new avenues for modulating the balance between plasticity and stability of the models. Comment: This manuscript has been submitted for consideration for publication in the Adaptive Behaviour Sage Journal, edited by Tom Froese |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1177/1059712320922916 |
| URL الوصول: | http://arxiv.org/abs/2001.01982 |
| رقم الأكسشن: | edsarx.2001.01982 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1177/1059712320922916 |
|---|