Authors introduce measurized MDPs as a measure-valued lifting of stochastic MDPs that generalizes the original setting and supports new constraints plus approximations via algebraic lifting and semicontinuous-semicompact analysis for average reward.
Bertsekas, Dimitri, and Steven E Shreve, 1996,Stochastic optimal control: the discrete-time case, volume 5 (Athena Scientific)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Measurized Markov Decision Processes
Authors introduce measurized MDPs as a measure-valued lifting of stochastic MDPs that generalizes the original setting and supports new constraints plus approximations via algebraic lifting and semicontinuous-semicompact analysis for average reward.