# Analogy making as amortised model construction

arXiv: https://arxiv.org/abs/2507.16511 · HTML: https://mlsanity.com/paper/2507.16511/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 46 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 11 of 11)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [Structured agents for physical construction](https://mlsanity.com/paper/1904.03177/) (2019)
- [People construct simplified mental representations to plan](https://mlsanity.com/paper/2105.06948/) (2021)
- [Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning](https://mlsanity.com/paper/2107.12544/) (2021)
- [Procedural Generalization by Planning with Self-Supervised World Models](https://mlsanity.com/paper/2111.01587/) (2021)
- [A Theory of Abstraction in Reinforcement Learning](https://mlsanity.com/paper/2203.00397/) (2022)
- [Synthesizing world models for bilevel planning](https://mlsanity.com/paper/2503.20124/) (2025)
- [Harmonizing Program Induction with Rate-Distortion Theory](https://mlsanity.com/paper/2405.05294/) (2024)

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

- [What Is Worth Representing? Representational Empowerment for Continual Model Construction](https://mlsanity.com/paper/2609.02322/) (2026)

## Abstract (arXiv)

Humans flexibly construct internal models to navigate novel situations. To be useful, these internal models must be sufficiently faithful to the environment that resource-limited planning leads to adequate outcomes; equally, they must be tractable to construct in the first place. We argue that analogy plays a central role in these processes, enabling agents to reuse solution-relevant structure from past experiences and amortise the computational costs of both model construction (construal) and planning. Formalising analogies as partial homomorphisms between Markov decision processes, we sketch a framework in which abstract modules, derived from previous construals, serve as composable building blocks for new ones. This modular reuse allows for flexible adaptation of policies and representations across domains with shared structural essence.