12 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre for Artificial Intelligence and RoboticsIN1 paper
- City University of New YorkUS1 paper
- European University CyprusCY1 paper
- Foundation for Research and Technology HellasGR1 paper
- Goddard Space Flight CenterUS1 paper
- Google DeepMind (United Kingdom)GB1 paper
- In-Q-TelUS1 paper
- Korea Institute for Advanced StudyKR1 paper
- Los Alamos National LaboratoryUS1 paper
- Northern Arizona UniversityUS1 paper
- The University of Texas at AustinUS1 paper
- University of California, Santa BarbaraUS1 paper
4 papers · 1 filter
Reward-Punishment Symmetric Universal Intelligence
Samuel Allen Alexander, Marcus Hutter
Can an agent's intelligence level be negative? We extend the Legg-Hutter agent-environment framework to include punishments and argue for an affirmative answer to that question. We…
Extending Environments To Measure Self-Reflection In Reinforcement Learning
Samuel Allen Alexander, Michael Castaneda, Kevin Compher +1
We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good perfo…
Measuring Intelligence and Growth Rate: Variations on Hibbard's Intelligence Measure
Samuel Alexander, Bill Hibbard
In 2011, Hibbard suggested an intelligence measure for agents who compete in an adversarial sequence prediction game. We argue that Hibbard's idea should actually be considered as…
Intelligence via ultrafilters: structural properties of some intelligence comparators of deterministic Legg-Hutter agents
Samuel Allen Alexander
Legg and Hutter, as well as subsequent authors, considered intelligent agents through the lens of interaction with reward-giving environments, attempting to assign numeric intellig…