Sciweavers

AGI
2015
7 years 11 months ago
Modeling Motivation in MicroPsi 2
The MicroPsi architecture combines neuro-symbolic representations with autonomous decision making and motivation based learning. MicroPsi’s motivational system reflects cognitive...
Joscha Bach
AGI
2015
7 years 11 months ago
Using Localization and Factorization to Reduce the Complexity of Reinforcement Learning
General reinforcement learning is a powerful framework for artificial intelligence that has seen much theoretical progress since introduced fifteen years ago. We have previously ...
Peter Sunehag, Marcus Hutter
AGI
2015
7 years 11 months ago
On the Limits of Recursively Self-Improving AGI
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...
Roman V. Yampolskiy
AGI
2015
7 years 11 months ago
Inferring Human Values for Safe AGI Design
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...
Can Eren Sezener
AGI
2015
7 years 11 months ago
Observation, Communication and Intelligence in Agent-Based Systems
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-...
AGI
2015
7 years 11 months ago
Are There Deep Reasons Underlying the Pathologies of Today's Deep Learning Algorithms?
Abstract. Some currently popular and successful deep learning architectures display certain pathological behaviors (e.g. confidently classifying random data as belonging to a fami...
Ben Goertzel
AGI
2015
7 years 11 months ago
Emotional Concept Development
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 ...
Claes Strannegård, Simone Cirillo, Johan Wes...
AGI
2015
7 years 11 months ago
Two Attempts to Formalize Counterpossible Reasoning in Deterministic Settings
This paper motivates the study of counterpossibles (logically impossible counterfactuals) as necessary for developing a decision theory suitable for generally intelligent agents e...
Nate Soares, Benja Fallenstein
AGI
2015
7 years 11 months ago
Can Machines Learn Logics?
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...
Chiaki Sakama, Katsumi Inoue
AGI
2015
7 years 11 months ago
Ultimate Intelligence Part I: Physical Completeness and Objectivity of Induction
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...
Eray Özkural