Parametric MDPs enable PAC uncertainty models for MDPs by projecting empirical frequencies onto parameter space with polytopic outer approximations, yielding tighter estimates than independent interval methods.
Model-based reinforcement learning with value-targeted regression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Parameter Learning for Uncertain MDPs
Parametric MDPs enable PAC uncertainty models for MDPs by projecting empirical frequencies onto parameter space with polytopic outer approximations, yielding tighter estimates than independent interval methods.