16 found
Order:
Disambiguations
Samuel Allen Alexander [11]Samuel A. Alexander [5]
See also
Samuel Allen Alexander
Ohio State University (PhD)
  1. The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI.Samuel Allen Alexander - 2020 - Journal of Artificial General Intelligence 11 (1):70-85.
    After generalizing the Archimedean property of real numbers in such a way as to make it adaptable to non-numeric structures, we demonstrate that the real numbers cannot be used to accurately measure non-Archimedean structures. We argue that, since an agent with Artificial General Intelligence (AGI) should have no problem engaging in tasks that inherently involve non-Archimedean rewards, and since traditional reinforcement learning rewards are real numbers, therefore traditional reinforcement learning probably will not lead to AGI. We indicate two possible ways (...)
    Download  
     
    Export citation  
     
    Bookmark   1 citation  
  2. Pseudo-visibility: A Game Mechanic Involving Willful Ignorance.Samuel Allen Alexander & Arthur Paul Pedersen - 2022 - FLAIRS-35.
    We present a game mechanic called pseudo-visibility for games inhabited by non-player characters (NPCs) driven by reinforcement learning (RL). NPCs are incentivized to pretend they cannot see pseudo-visible players: the training environment simulates an NPC to determine how the NPC would act if the pseudo-visible player were invisible, and penalizes the NPC for acting differently. NPCs are thereby trained to selectively ignore pseudo-visible players, except when they judge that the reaction penalty is an acceptable tradeoff (e.g., a guard might accept (...)
    Download  
     
    Export citation  
     
    Bookmark   1 citation  
  3. Reward-Punishment Symmetric Universal Intelligence.Samuel Allen Alexander & Marcus Hutter - 2021 - In AGI.
    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 show that if the background encodings and Universal Turing Machine (UTM) admit certain Kolmogorov complexity symmetries, then the resulting Legg-Hutter intelligence measure is symmetric about the origin. In particular, this implies reward-ignoring agents have Legg-Hutter intelligence 0 according to such UTMs.
    Download  
     
    Export citation  
     
    Bookmark   1 citation  
  4. A Machine That Knows Its Own Code.Samuel A. Alexander - 2014 - Studia Logica 102 (3):567-576.
    We construct a machine that knows its own code, at the price of not knowing its own factivity.
    Download  
     
    Export citation  
     
    Bookmark   3 citations  
  5. Universal Agent Mixtures and the Geometry of Intelligence.Samuel Allen Alexander, David Quarel, Len Du & Marcus Hutter - 2023 - Aistats.
    Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's intelligence is (...)
    Download  
     
    Export citation  
     
    Bookmark  
  6. Infinite graphs in systematic biology, with an application to the species problem.Samuel A. Alexander - 2013 - Acta Biotheoretica 61 (2):181--201.
    We argue that C. Darwin and more recently W. Hennig worked at times under the simplifying assumption of an eternal biosphere. So motivated, we explicitly consider the consequences which follow mathematically from this assumption, and the infinite graphs it leads to. This assumption admits certain clusters of organisms which have some ideal theoretical properties of species, shining some light onto the species problem. We prove a dualization of a law of T.A. Knight and C. Darwin, and sketch a decomposition result (...)
    Download  
     
    Export citation  
     
    Bookmark   2 citations  
  7. Extending Environments To Measure Self-Reflection In Reinforcement Learning.Samuel Allen Alexander, Michael Castaneda, Kevin Compher & Oscar Martinez - 2022 - Journal of Artificial General Intelligence 13 (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 performance usually requires paying attention to whatever things the environment's outputs are based on, we argue that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect. Thus weighted-average performance over the space of all suitably well-behaved extended environments could be considered a (...)
    Download  
     
    Export citation  
     
    Bookmark   2 citations  
  8. Knowledge-of-own-factivity, the definition of surprise, and a solution to the Surprise Examination paradox.Alessandro Aldini, Samuel Allen Alexander & Pierluigi Graziani - 2022 - Cifma.
    Fitch's Paradox and the Paradox of the Knower both make use of the Factivity Principle. The latter also makes use of a second principle, namely the Knowledge-of-Factivity Principle. Both the principle of factivity and the knowledge thereof have been the subject of various discussions, often in conjunction with a third principle known as Closure. In this paper, we examine the well-known Surprise Examination paradox considering both the principles on which this paradox rests and some formal characterisations of the surprise notion, (...)
    Download  
     
    Export citation  
     
    Bookmark  
  9. Private memory confers no advantage.Samuel Allen Alexander - forthcoming - Cifma.
    Mathematicians and software developers use the word "function" very differently, and yet, sometimes, things that are in practice implemented using the software developer's "function", are mathematically formalized using the mathematician's "function". This mismatch can lead to inaccurate formalisms. We consider a special case of this meta-problem. Various kinds of agents might, in actual practice, make use of private memory, reading and writing to a memory-bank invisible to the ambient environment. In some sense, we humans do this when we silently subvocalize (...)
    Download  
     
    Export citation  
     
    Bookmark  
  10. Self-referential theories.Samuel A. Alexander - 2020 - Journal of Symbolic Logic 85 (4):1687-1716.
    We study the structure of families of theories in the language of arithmetic extended to allow these families to refer to one another and to themselves. If a theory contains schemata expressing its own truth and expressing a specific Turing index for itself, and contains some other mild axioms, then that theory is untrue. We exhibit some families of true self-referential theories that barely avoid this forbidden pattern.
    Download  
     
    Export citation  
     
    Bookmark  
  11. Arithmetical algorithms for elementary patterns.Samuel A. Alexander - 2015 - Archive for Mathematical Logic 54 (1-2):113-132.
    Elementary patterns of resemblance notate ordinals up to the ordinal of Pi^1_1-CA_0. We provide ordinal multiplication and exponentiation algorithms using these notations.
    Download  
     
    Export citation  
     
    Bookmark   1 citation  
  12. Fast-Collapsing Theories.Samuel A. Alexander - 2013 - Studia Logica (1):1-21.
    Reinhardt’s conjecture, a formalization of the statement that a truthful knowing machine can know its own truthfulness and mechanicalness, was proved by Carlson using sophisticated structural results about the ordinals and transfinite induction just beyond the first epsilon number. We prove a weaker version of the conjecture, by elementary methods and transfinite induction up to a smaller ordinal.
    Download  
     
    Export citation  
     
    Bookmark   1 citation  
  13. Can reinforcement learning learn itself? A reply to 'Reward is enough'.Samuel Allen Alexander - 2021 - Cifma.
    In their paper 'Reward is enough', Silver et al conjecture that the creation of sufficiently good reinforcement learning (RL) agents is a path to artificial general intelligence (AGI). We consider one aspect of intelligence Silver et al did not consider in their paper, namely, that aspect of intelligence involved in designing RL agents. If that is within human reach, then it should also be within AGI's reach. This raises the question: is there an RL environment which incentivises RL agents to (...)
    Download  
     
    Export citation  
     
    Bookmark  
  14. Did Socrates know how to see your middle eye?Samuel Allen Alexander & Christopher Yang - 2021 - The Reasoner 15 (4):30-31.
    We describe in our own words a visual phenomenon first described by Gallagher and Tsuchiya in 2020. The key to the phenomenon (as we describe it) is to direct one’s left eye at the image of one's left eye, while simultaneously directing one's right eye at the image of one's right eye. We suggest that one would naturally arrive at this phenomenon if one took a sufficiently literal reading of certain words of Socrates preserved in Plato's Alcibiades. We speculate that (...)
    Download  
     
    Export citation  
     
    Bookmark  
  15. Extended subdomains: a solution to a problem of Hernández-Orallo and Dowe.Samuel Allen Alexander - 2022 - In AGI.
    This is a paper about the general theory of measuring or estimating social intelligence via benchmarks. Hernández-Orallo and Dowe described a problem with certain proposed intelligence measures. The problem suggests that those intelligence measures might not accurately capture social intelligence. We argue that Hernández-Orallo and Dowe's problem is even more general than how they stated it, applying to many subdomains of AGI, not just the one subdomain in which they stated it. We then propose a solution. In our solution, instead (...)
    Download  
     
    Export citation  
     
    Bookmark  
  16. An Alternative Construction of Internodons: The Emergence of a Multi-level Tree of Life.Samuel Allen Alexander, Arie de Bruin & D. J. Kornet - 2015 - Bulletin of Mathematical Biology 77 (1):23-45.
    Internodons are a formalization of Hennig's concept of species. We present an alternative construction of internodons imposing a tree structure on the genealogical network. We prove that the segments (trivial unary trees) from this tree structure are precisely the internodons. We obtain the following spin-offs. First, the generated tree turns out to be an organismal tree of life. Second, this organismal tree is homeomorphic to the phylogenetic Hennigian species tree of life, implying the discovery of a multi-level tree of life: (...)
    Download  
     
    Export citation  
     
    Bookmark