NAVIGATION
Home
Research
Bookshelf
Garden
FIND ME ON
GitHub
LinkedIn
🌱
A deterministic Markov control policy γ∈ΓM\gamma\in\Gamma_{M}γ∈ΓM is a sequence of functions {γt}\{ \gamma_{t} \}{γt} s.t. γt:X×Z+→U\gamma_{t}:\mathbb{X}\times \mathbb{Z}_{+}\to \mathbb{U}γt:X×Z+→Uand ut=γt(xt)u_{t}=\gamma_{t}(x_{t})ut=γt(xt)∀t∈Z+\forall t\in\mathbb{Z}_{+}∀t∈Z+.
Markov Policy induces Markov Chain
Markov Policy is Good Enough