3 papers
cs.AI2026
Path-dependent program induction under resource constraints explains human sequence learning
Hanqi Zhou, David G. Nagy, Peter Dayan +1
How do people build abstract, reusable knowledge from sequential experience under bounded cognitive resources? To answer this question, we integrate rate-distortion theory with rec…
cs.LG2025
Agent-centric learning: from external reward maximization to internal knowledge curation
Hanqi Zhou, Fryderyk Mantiuk, David G. Nagy +1
The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, h…
cs.LG2025
Analogy making as amortised model construction
David G. Nagy, Tingke Shen, Hanqi Zhou +2
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 p…