Doing more with less: meta-reasoning and meta-learning in humans and machines

By T. Griffiths, Frederick Callaway, Michael Chang, Erin Grant, Falk Lieder. 2019

134 citations recorded by the source corpus.

Artificial intelligence systems use an increasing amount of computation and data to solve very specific problems. By contrast, human minds solve a wide range of problems using a fixed amount of computation and limited experience. We identify two abilities that we see as crucial to this kind of general intelligence: meta-reasoning (deciding how to allocate computational resources) and meta-learning (modeling the learning environment to make better use of limited data). We summarize the relevant AI literature and relate the resulting ideas to recent work in psychology.

Subfields: Artificial Intelligence, Meta & Continual Learning, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Meta & Continual Learning

In Cognitive Science & Psychology

Citations in the corpus

Flamingo: a Visual Language Model for Few-Shot Learning (2022, background): “One key aspect of intelligence is the ability to quickly learn to perform a new task given a short instruction [33, 70].”
Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “To achieve this, continual learning agents should reuse aspects of the solutions to previously solved subproblems through function composition (Griffiths et al., 2019) by abstracting relevant meaningful information in the form of abstract concepts (Parr and Russell, 1998) or skills (Thrun and Schwar”
Automatically Composing Representation Transformations as a Means for Generalization (2018, background): “s required for a family of problems. A major challenge would be to discover the subproblem decomposition without a curriculum and without domain-speciﬁc constraints on the model class of the modules. Grifﬁths et al. (2019) argued that the efﬁcient use cognitive resources in humans may also explain t”
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization (2021, background): “…learning agents need to ﬁnd structure in the world to tackle new tasks by decomposing them in smaller sub-problems through function composition (Grifﬁths et al. 2019) or by extracting meaningful information in the form of abstract concepts (Zhang, Satija, and Pineau 2018; Francois-Lavet et al.…”