NAVIGATION
Home
Research
Bookshelf
Garden
FIND ME ON
GitHub
LinkedIn
🌱
Let X\mathbb{X}X be a Borel space and let f:X→Rf:\mathbb{X}\to \mathbb{R}f:X→R be a Borel function. We define the bounded-Lipschitz Norm as ∥f∥BL:=∥f∥∞+supx≠y∣f(x)−f(y)∣d(x,y)\lVert f \rVert _{BL}:=\lVert f \rVert _{\infty}+\sup_{x\not=y}\frac{|f(x)-f(y)|}{d(x,y)}∥f∥BL:=∥f∥∞+x=ysupd(x,y)∣f(x)−f(y)∣
Let μ,ν∈P(X)\mu,\nu \in\mathcal{P}(\mathbb{X})μ,ν∈P(X) we define the bounded Lipschitz metric as ρBL(μ,ν):=sup∥f∥BL≤1∣∫f dμ−∫f dν∣\rho_{BL}(\mu,\nu):=\sup_{\lVert f \rVert _{BL}\le 1}\left|\int\limits f \, d\mu-\int\limits f \, d\nu \right|ρBL(μ,ν):=∥f∥BL≤1sup∫fdμ−∫fdν
Belief MDP
Filter Stability
Required Conditions for Finite Memory Q-learning