Lab Algoritma dan Komputasi
Universitas Gadjah Mada
Beranda
Profil Lab
Anggota Lab
Proyek Lab
Publikasi
Kontak
Resource
k-Armed Bandit
Markov Decision Process
Current State:
S1
Start Episode
Action a1
Action a2
Average Reward per Episode:
0.00
Total Reward:
0.00
Episode 0 of 5
Episode Total Reward: 0
Episode Length: 0
No action taken.
Episode Log: