Work cat.: Reinforcement learning, c1992 (Reinforcement learning is the learning of a mapping from situations to actions so as to maximize a scalar reward or reinforcement signal ... One could consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes, e.g. operant conditioning and secondary reinforcement.)

Encyc. artific. intel.: p. 232, under Demons--Learning)

Facts file dict. artific. intel.

Random House; McGraw-Hill dict. sci. tech.; Computer dict.