One of the major ways that people engage in adaptive problemsolving is by copying the solutions of others. Most of the workon this field has focused on three questions: when to copy, whoto copy from, and what to copy. However, how much to copyhas been relatively less explored. In the current research, weare interested in the consequences for a group when its mem-bers engage in social learning strategies with different tenden-cies to copy entire or partial solutions and different complex-ities of search problems. We also consider different networktopologies that affect the solutions visible to each member.Using a computational model of collective problem solving,we demonstrate that strategies where social learning involvespartial copying outperform strategies where individuals copyentire solutions. We analyze the exploration/exploitation dy-namics of these social learning strategies under the differentconditions.