When Does Bounded-Optimal Metareasoning Favor Few Cognitive Systems?
Lists
Only you see this
Abstract
While optimal metareasoning is notoriously intractable, humans are nonetheless able to adaptively allocate their computational resources. A possible approximation that humans may use to do this is to only metareason over a finite set of cognitive systems that perform variable amounts of computation. The highly influential "dual-process" accounts of human cognition, which postulate the coexistence of a slow accurate system with a fast error-prone system, can be seen as a special case of this approximation. This raises two questions: how many cognitive systems should a bounded optimal agent be equipped with and what characteristics should those systems have? We investigate these questions in two settings: a one-shot decision between two alternatives, and planning under uncertainty in a Markov decision process. We find that the optimal number of systems depends on the variability of the environment and the costliness of metareasoning. Consistent with dual-process theories, we also find that when having two systems is optimal, then the first system is fast but error-prone and the second system is slow but accurate.
BibTeX
@inproceedings{milli2017when,
author = {Smitha Milli and Falk Lieder and Thomas L. Griffiths},
title = {{When Does Bounded-Optimal Metareasoning Favor Few Cognitive Systems?}},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2017},
doi = {10.1609/aaai.v31i1.11156},
}| Ideal Partition of Resources for Metareasoning | arXiv · 2021 |
| Definition and Complexity of Some Basic Metareasoning Problems | IJCAI · 2003 |
| Learning to select computations | arXiv · 2017 |
| Thinking Fast and Slow in AI: the Role of Metacognition | arXiv · 2021 |
| Where Do Human Heuristics Come From? | arXiv · 2019 |
| A Unified Theory of Dual-Process Control | arXiv · 2022 |