Three different training programmes for a word processing system were experimentally compared: (1) a sequential programme, which taught low-level skills and which did not help the user actively to develop a mental model, (2) a hierarchical programme, which provided an explicit and integrated conceptual model of the system to the user and (3) a programme in which the users were asked to develop hypotheses on the functioning of the software and in which they were encouraged to use an active and exploratory approach. From an action theory point of view it was hypothesized that the third group would be superior to the first group. In an experimental study with two training sessions each of two hours and a two-hour testing session (n = 15), this was shown to be the case for several performance criteria (error time, transfer and experimenter rating). Additionally, an interindividual difference variable lo measure the individual learning style was used, giving results that could be interpreted in a similar way to the experimental results. © 1988 Taylor & Francis Group, LLC.