AI RESEARCH
The Value of Mechanistic Priors in Sequential Decision Making
arXiv CS.LG
•
ArXi:2605.10018v1 Announce Type: new Hybrid mechanistic models, physical priors with learned residuals, promise to reduce the data required for good decisions, but have no computable criterion to test this. We characterize the value of mechanistic priors in sequential decision-making within both asymptotic and burn-in regimes. To formalize this, we