A two-step algorithm for learning from unspecific reinforcement

We study a simple learning model based on the Hebb rule to cope with 'delayed', unspecific reinforcement. In spite of the unspecific nature of the information-feedback convergence to asymptotically perfect generalization is observed, with a rate depending, however, in a nonuniversal way on learning parameters. Asymptotic convergence can be as fast as that of Hebbian learning, but may be slower. Morever, for a certain range of parameter settings, it depends on initial conditions whether the system can reach the regime of asymptotically perfect generalization, or rather approaches a stationary state of poor generalization.