Before We Can Find a Model, We Must Forget about Perfection
Dimiter Dobrev · 2022 · Serdica Journal of Computing
WASTE classifies this as Abandoned Hypothesis · AI classification, approximate
A hypothesis was tested and not supported — a dead end worth knowing about before you pursue it.
Abstract (excerpt)
With Reinforcement Learning we assume that a model of the world does exist. We assume furthermore that the model in question is perfect (i.e. it describes the world completely and unambiguously). This article will demonstrate that it does…
Excerpt shown for reference under fair use — read the full paper at the publisher.
Hosted by the publisher — may require access.
About to run something similar?
Run an AI Precheck on your own design to catch failure modes like this one before you spend the time. Your first desk check is free.
Related failures
Are we ready to genetically modify a human embryo? Or is it too late to ask?
Abandoned HypothesisStatistically responsible artificial intelligences
Abandoned HypothesisEditorial Commentary: Anterolateral Ligament: How Do We Find It?
Abandoned HypothesisEditorial Commentary: Long Head Biceps Pathology: How Do We Find It?
Abandoned HypothesisThe Failed Reader: Keats’s “Brain-Sick” Endymion
Abandoned HypothesisClinical and microbiological features of infection in alcoholic hepatitis: an international cohort study
WASTE indexes this work — it does not host or republish it. Failure-type classification is automated and approximate.
Metadata source: Crossref · DOI 10.55630/sjc.2021.15.85-128