Occam's razor is insufficient to infer the preferences of irrational agents

Authors: Stuart Armstrong, Sören Mindermann

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper shows (1) that a No Free Lunch result implies it is impossible to uniquely decompose a policy into a planning algorithm and reward function, and (2) that even with a reasonable simplicity prior/Occam s razor on the set of decompositions, we cannot distinguish between the true decomposition and others that lead to high regret. To address this, we need simple normative assumptions, which cannot be deduced exclusively from observations.
Researcher Affiliation Academia S oren Mindermann * Vector Institute University of Toronto soeren.mindermann@gmail.com Stuart Armstrong* Future of Humanity Institute University of Oxford stuart.armstrong@philosophy.ox.ac.uk Further affiliation: Machine Intelligence Research Institute, Berkeley, USA.
Pseudocode No The paper presents theoretical concepts, definitions, lemmas, propositions, and proofs but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper is theoretical and does not mention or provide access to any source code for the described methodology.
Open Datasets No The paper is a theoretical work and does not use or reference any publicly available datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not conduct experiments involving dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any hardware used for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not detail any experimental setup, hyperparameters, or training configurations.