NAVIGATION
Home
Research
Bookshelf
Garden
FIND ME ON
GitHub
LinkedIn
🌱
An ε-optimal policy is a Policy whose performance is within ϵ\epsilonϵ of the Optimal policy, where ϵ≥0\epsilon \geq 0ϵ≥0 is a small number representing the acceptable margin of sub-optimality. i.e. A policy γ∗\gamma^{*}γ∗ is ε-optimal if, ∀γ\forall \gamma∀γ: J(γ)≥J(γ∗)−ϵJ(\gamma) \geq J(\gamma^{*}) - \epsilonJ(γ)≥J(γ∗)−ϵ
Q-Learning