The MicroPsi architecture combines neuro-symbolic representations with autonomous decision making and motivation based learning. MicroPsi’s motivational system reflects cognitive...
General reinforcement learning is a powerful framework for artificial intelligence that has seen much theoretical progress since introduced fifteen years ago. We have previously ...
Self-improving software has been a goal of computer scientists since the founding of the field of Artificial Intelligence. In this work we analyze limits on computation which might...
Abstract. Aligning goals of superintelligent machines with human values is one of the ways to pursue safety in AGI systems. To achieve this, it is first necessary to learn what hu...
The intelligence of multiagent systems is known to depend on the communication and observation abilities of its agents. However it is not clear which factor has the greater influe...
Nader Chmait, David L. Dowe, David G. Green, Yuan-...
Abstract. Some currently popular and successful deep learning architectures display certain pathological behaviors (e.g. confidently classifying random data as belonging to a fami...
Abstract. Artificial emotions of different varieties have been used for controlling behavior, e.g. in cognitive architectures and reinforcement learning models. We propose to use ...
This paper motivates the study of counterpossibles (logically impossible counterfactuals) as necessary for developing a decision theory suitable for generally intelligent agents e...
This paper argues the possibility of designing AI that can learn logics from data. We provide an abstract framework for learning logics. In this framework, an agent A provides trai...
We propose that Solomonoff induction is complete in the physical sense via several strong physical arguments. We also argue that Solomonoff induction is fully applicable to quant...