Social learning is an important collective behaviour in many biological and artificial systems. We investigate a model of social learning which combines two distinct processes, one relating to how individuals adapt their beliefs as a result of interacting with their peers, and one relating to when they search for and how they learn directly from evidence. For each process we introduce conservative and open-minded behaviours and combine these to obtain four social learning behaviour types. A simple truth-seeking task is considered and a three-valued model of belief states is adopted. By means of difference equation models and agent-based simulations we then investigate the performance of the different learning behaviours. We show that certain heterogeneous mixtures of behaviours result in the most robust performance for a variety of learning rates and initial conditions, and that such mixtures are well suited for social learning in dynamic environments.