subdomains
www
newsletter
communities
abhinav-ja.in
F(x) → ℝ^d
P(a|s) = 0.98
σ(z)
x₁, x₂
q* = argmax
Q(s, a)
v ≈ 12ms
π(a|s,θ)
confidence
0.98
state
latency
12ms
Posts
About
Posts
About