# What are the mechanisms underlying metacognitive learning?

arXiv: https://arxiv.org/abs/2302.04840 · HTML: https://mlsanity.com/paper/2302.04840/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 38 references that are in the map.
- First posted on arXiv 9 Feb 2023.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Tempered Sigmoid Activations for Deep Learning with Differential Privacy](https://mlsanity.com/paper/2007.14191/) (2020)
- [Learning to select computations](https://mlsanity.com/paper/1711.06892/) (2017)
- [Have I done enough planning or should I plan more?](https://mlsanity.com/paper/2201.00764/) (2022)

## Built on by (most cited first, 2 of 2)

- [Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics](https://mlsanity.com/paper/2501.06762/) (2025)
- [Individual differences in the cognitive mechanisms of planning strategy discovery](https://mlsanity.com/paper/2505.23519/) (2025)

## Abstract (arXiv)

How is it that humans can solve complex planning tasks so efficiently despite limited cognitive resources? One reason is its ability to know how to use its limited computational resources to make clever choices. We postulate that people learn this ability from trial and error (metacognitive reinforcement learning). Here, we systematize models of the underlying learning mechanisms and enhance them with more sophisticated additional mechanisms. We fit the resulting 86 models to human data collected in previous experiments where different phenomena of metacognitive learning were demonstrated and performed Bayesian model selection. Our results suggest that a gradient ascent through the space of cognitive strategies can explain most of the observed qualitative phenomena, and is therefore a promising candidate for explaining the mechanism underlying metacognitive learning.