Current Phase
Ready to start
UCB1 Formula
UCB1 = Q̄(a) + c·√(ln N / n(a))
c = 1.41 (√2)
Balances exploitation (high Q̄) with exploration (low n)
c = 1.41 (√2)
Balances exploitation (high Q̄) with exploration (low n)
Statistics
Iterations: 0
Total simulations: 0
Total simulations: 0
UCB1 Scores (Root Children)
Not yet computed