Analogy making as amortised model construction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912496738107392 |
|---|---|
| author | Nagy, David G. Shen, Tingke Zhou, Hanqi Wu, Charley M. Dayan, Peter |
| author_facet | Nagy, David G. Shen, Tingke Zhou, Hanqi Wu, Charley M. Dayan, Peter |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16511 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Analogy making as amortised model construction Nagy, David G. Shen, Tingke Zhou, Hanqi Wu, Charley M. Dayan, Peter Machine Learning Artificial Intelligence 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. |
| title | Analogy making as amortised model construction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.16511 |