exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payoff) …

's dilemma payoff matrix (S, R, T, P) = (-2, 2, 4, 0). Twenty-one different combinations of these parameters were used in the …

show that for all specifications of priorbeliefs and payoff-generating processes that satisfy some separability condition … current payoff of the risky arm and the expected full-information payoff, given current information. The separability …'s expected payoff per unit of time is time-invariant and actual payoffs are generated by a process with independent and …