Spiking neural controllers for pushing objects around
Razvan V. Florian
Simulation of Adaptive Behavior 2006 (SAB 2006)
Rome, Italy, 25-29 September 2006
Summary
We evolve spiking neural networks that implement a seek-push-release drive for a simple simulated agent interacting with objects. The networks have either static synapses or synapses featuring spike-timing-dependent plasticity (STDP). Both types of networks were able to solve the task, but networks with plastic synapses evolved faster. In the evolved networks, plasticity plays a minor role during the interaction with the environment and is used mostly to tune synapses when networks start to function. The agents controlled by the evolved networks adapt their interaction to objects as a function of relative object size.