Dubey, Griffiths, and Dayan 2022

Source of the happiness function f[h] that this paper extends with pain-belief

Neighborhood — ranked by edge-count

paper

method

Happiness Function f[h]
cites
Subjective reward signal from Dubey et al. 2022 balancing objective reward, expectations, and comparisons; extended in this paper

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Watkins and Dayan 1992concept0.749
Original Q-Learning paper cited for the learning algorithm used in all agents
Mahajan, Dayan, and Seymour 2025concept0.744
Casts pain and injury as POMDPs; direct precursor to this paper's approach
David Humeconcept0.670
Associated with empiricist regularity theory of causation that Juarrero argues is inadequate for action explanation.
Dravid et al. (2023)concept0.664
Found Rosetta Neurons — neurons activated by same patterns across diverse vision models
Singh, Lewis, and Barto 2009concept0.660
Source of the optimal reward framework used to evaluate and select best reward functions
Yamins et al. (2014)concept0.658
Showed that performance-optimized neural networks align with biological brain representations in higher visual cortex
Abdou et al. (2021)concept0.656
Discovered that color distances in language representations mirror human perceptual distances; reproduced and extended in this paper