research
∙
07/11/2023
Strengthening Consistency Results in Modal Logic
A fundamental question asked in modal logic is whether a given theory is...
share
research
∙
02/13/2023
Universal Agent Mixtures and the Geometry of Intelligence
Inspired by recent progress in multi-agent Reinforcement Learning (RL), ...
research
∙
10/13/2021
Extending Environments To Measure Self-Reflection In Reinforcement Learning
We consider an extended notion of reinforcement learning in which the en...
research
∙
10/06/2021
Reward-Punishment Symmetric Universal Intelligence
Can an agent's intelligence level be negative? We extend the Legg-Hutter...
research
∙
05/09/2020
AGI and the Knight-Darwin Law: why idealized AGI reproduction requires collaboration
Can an AGI create a more intelligent AGI? Under idealized assumptions, f...
research
∙
02/15/2020
The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI
After generalizing the Archimedean property of real numbers in such a wa...
research
∙
12/03/2019
Measuring the intelligence of an idealized mechanical knowing agent
We define a notion of the intelligence level of an idealized mechanical ...
research
∙
10/22/2019