A formal theory proves model exploitation is essentially unavoidable on large policy sets in RL, generalizes reward hacking results, and derives a safe horizon for a relaxed version of exploitation.
Journal of Mathematical Analysis and Applications , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Temporal difference calibration aligns uncertainty estimates in vision-language-action models with their value functions for better sequential performance.
citing papers explorer
-
Imperfect World Models are Exploitable
A formal theory proves model exploitation is essentially unavoidable on large policy sets in RL, generalizes reward hacking results, and derives a safe horizon for a relaxed version of exploitation.
-
Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
Temporal difference calibration aligns uncertainty estimates in vision-language-action models with their value functions for better sequential performance.