Shiv Contractor, Michael Moosmeier, Sebastian Schuon
Research Paths Towards Thinking A.I.
2018

Sagel, Alexander; Gottwald, Martin
Never Mind the Density, Here's the Level Set
NeurIPS Workshop on Bayesian Deep Learning
2018

Gottwald, Martin;Guo, Mingpan;Shen, Hao
Neural Value Function Approximation in Continuous State Reinforcement Learning Problems
European Workshop on Reinforcement Learning 14 (2018)
Lille, France
2018

Berberich, Nicolas;Diepold, Klaus
The Virtuous Machine - Old Ethics for New Technology?
Modern AI and robotic systems are characterized by a high and ever-increasing level of autonomy. At the same time, their applications in fields such as autonomous driving, service robotics and digital personal assistants move closer to humans. From the combination of both developments emerges the field of AI ethics which recognizes that the actions of autonomous machines entail moral dimensions and tries to answer the question of how we can build moral machines. In this paper we argue for taking inspiration from Aristotelian virtue ethics by showing that it forms a suitable combination with modern AI due to its focus on learning from experience. We furthermore propose that imitation learning from moral exemplars, a central concept in virtue ethics, can solve the value alignment problem. Finally, we show that an intelligent system endowed with the virtues of temperance and friendship to humans would not pose a control problem as it would not have the desire for limitless self-improvement.
2018

Aykın, Can;Knopp, Martin;Diepold, Klaus
Deep Reinforcement Learning for Formation Control
1124-1128
27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2018)
Nanjing, China
Institute of Electrical and Electronics Engineers (IEEE)
2018