原书出处
Causal AI
various constraints. For one example with a given allocation outcome in the log, we could generate a counterfactual outcome for that example by applying a different allocation policy to that example. Similarly, given data produced by simulation software, we could generate counterfactual data by changing the simulation to reflect a hypothetical condition and then rerunning it with the same initial conditions as the original data.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-10.xhtml
EPUB SHA-256:e55e7dc9d7966ea79311f2bc8d5bef7371a6dbb65240f11a2b3e44180b934e72