kaal:claim:7456999-023

The incomplete-contracts comparison treats out-of-distribution behavior as unresolved, but remains an analogy rather than a derivation of reward overoptimization.

An RLHF reward model can be viewed as specifying reward for the training distribution while leaving out-of-distribution behavior unresolved. This comparison is an analogy, not a derivation of reward overoptimization.

Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026), II.B Analogies: Arrow and Grossman-Hart-Moore, p. 8
https://ssrn.com/abstract=7456999 · source PDF

Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026). SSRN: https://ssrn.com/abstract=7456999

• the paper's use of the incomplete-contracts literature

methodologicalsupport: arguedeconomicsai-and-agentsresearch-methods

The quote above is an exact passage from the source PDF, whose sha256 is 01016fbbcc25cad205cebd59ea686d8dfee8ae9b632095d86ba6c9a900456a4b.
Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/7456999-023.md | sha256sum