# The Construction of Reality in an AI: A Review

arXiv: https://arxiv.org/abs/2302.05448 · HTML: https://mlsanity.com/paper/2302.05448/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 772 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 30 of 34)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [Imagination-Augmented Agents for Deep Reinforcement Learning](https://mlsanity.com/paper/1707.06203/) (2017)
- [Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments](https://mlsanity.com/paper/1710.03641/) (2017)
- [Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions](https://mlsanity.com/paper/1802.10353/) (2018)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner](https://mlsanity.com/paper/1607.08723/) (2016)
- [The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization](https://mlsanity.com/paper/2110.07732/) (2021)
- [Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics](https://mlsanity.com/paper/1706.04317/) (2017)
- [Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex](https://mlsanity.com/paper/1511.00083/) (2015)
- [How Can We Be So Dense? The Benefits of Using Highly Sparse Representations](https://mlsanity.com/paper/1903.11257/) (2019)
- [Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs](https://mlsanity.com/paper/1812.02788/) (2018)
- [Teaching Compositionality to CNNs](https://mlsanity.com/paper/1706.04313/) (2017)
- [Early Visual Concept Learning with Unsupervised Deep Learning](https://mlsanity.com/paper/1606.05579/) (2016)
- [Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration](https://mlsanity.com/paper/2109.08603/) (2021)
- [Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning](https://mlsanity.com/paper/1909.03906/) (2019)
- [Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images](https://mlsanity.com/paper/1504.06692/) (2015)
- [Understanding Early Word Learning in Situated Artificial Agents](https://mlsanity.com/paper/1710.09867/) (2017)
- [Unicorn: Continual Learning with a Universal, Off-policy Agent](https://mlsanity.com/paper/1802.08294/) (2018)
- [Learning to Crawl](https://mlsanity.com/paper/1905.12781/) (2019)
- [Hippocampal Spatial Mapping As Fast Graph Learning](https://mlsanity.com/paper/2107.00567/) (2021)
- [Balancing New Against Old Information: The Role of Surprise in Learning](https://mlsanity.com/paper/1606.05642/) (2016)

## Built on by (most cited first, 1 of 1)

- [A Case for AI Safety via Law](https://mlsanity.com/paper/2309.12321/) (2023)

## Abstract (arXiv)

AI constructivism as inspired by Jean Piaget, described and surveyed by Frank Guerin, and representatively implemented by Gary Drescher seeks to create algorithms and knowledge structures that enable agents to acquire, maintain, and apply a deep understanding of the environment through sensorimotor interactions. This paper aims to increase awareness of constructivist AI implementations to encourage greater progress toward enabling lifelong learning by machines. It builds on Guerin's 2008 "Learning Like a Baby: A Survey of AI approaches." After briefly recapitulating that survey, it summarizes subsequent progress by the Guerin referents, numerous works not covered by Guerin (or found in other surveys), and relevant efforts in related areas. The focus is on knowledge representations and learning algorithms that have been used in practice viewed through lenses of Piaget's schemas, adaptation processes, and staged development. The paper concludes with a preview of a simple framework for constructive AI being developed by the author that parses concepts from sensory input and stores them in a semantic memory network linked to episodic data. Extensive references are provided.