pi
Say it “pi”
About 3.14159 — the circle constant. In RL, π is a policy instead.
Example
An RL policy: probability of action a in state s.
In code
np.pitorch.piWhere you’ll see it in ML
Gaussian formulas contain π; RL uses π for policies.
Say it “pi”
About 3.14159 — the circle constant. In RL, π is a policy instead.
An RL policy: probability of action a in state s.
np.pitorch.piGaussian formulas contain π; RL uses π for policies.