AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

When Does Bounded-Optimal Metareasoning Favor Few Cognitive Systems?

Smitha Milli, Falk Lieder, Thomas Griffiths

AAAI 2017 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase variability of the environment (Var(re))bounded-optimal metareasoning agent · 2AFC and grid-world planningoptimal number of systemsImproved
increase metareasoning cost (lower 1/rm... i.e. costlier metareasoning)bounded-optimal metareasoning agent · 2AFC and grid-world planningoptimal number of systemsHurt
add additional cognitive systems beyond the firstbounded-optimal agent · 2AFCexpected utility per timeNo clear effect
increase environment variance when two systems are optimaltwo-system agent · 2AFC (Table 1)gap between systems' sample counts: 3, 5 -> 1, 7Improved
add first planning system (vs. 0 rollouts)grid-world agent · 20x20 grid worldexpected costImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy