Shaping is a
conditioning paradigm used primarily in the
experimental analysis of behavior. The method used is
differential reinforcement of
successive approximations. It was introduced by
B.F. Skinner with pigeons and extended to dogs, dolphins, humans and other species. In shaping, the form of an existing response is gradually changed across successive trials towards a desired target behavior by rewarding exact segments of behavior. Skinner's explanation of shaping was this:
Successive approximations
The successive approximations reinforced are increasingly accurate approximations of a response desired by a trainer. As training progresses the trainer stops reinforcing the less accurate approximations. For example, in training a rat to press a lever, the following successive approximations might be reinforced:
- simply turning toward the lever will be reinforced
- only stepping toward the lever will be reinforced
- only moving to within a specified distance from the lever will be reinforced
- only touching the lever with any part of the body, such as the nose, will be reinforced
- only touching the lever with a specified paw will be reinforced
- only depressing the lever partially with the specified paw will be reinforced
- only depressing the lever completely with the specified paw will be reinforced