Search Results - "Soltoggio, A."

Solving the distal reward problem with rare correlations by Soltoggio, Andrea, Steil, Jochen J

“…In the course of trial-and-error learning, the results of actions, manifested as rewards or punishments, occur often seconds after the actions that caused…”
Get more information

Evolving neuromodulatory topologies for reinforcement learning-like problems by Soltoggio, A., Durr, P., Mattiussi, C., Floreano, D.

“…Environments with varying reward contingencies constitute a challenge to many living creatures. In such conditions, animals capable of adaptation and learning…”
Get full text

Neural Plasticity and Minimal Topologies for Reward-Based Learning by Soltoggio, A.

“…Artificial neural networks for online learning problems are often implemented with synaptic plasticity to achieve adaptive behaviour. A common problem is that…”
Get full text

Using movement primitives in interpreting and decomposing complex trajectories in learning-by-doing by Soltoggio, A., Lemme, A., Steil, J. J.

“…Learning and reproducing complex movements is an important skill for robots. However, while humans can learn and generalise new complex trajectories, robots…”
Get full text

GP and GA in the design of a constrained control system with disturbance rejection by Soltoggio, A.

“…The design of a robust controller for a constrained SISO linear system is considered. Initially, the study of a solution provided by genetic programming (GP)…”
Get full text

Evolvability of Neuromodulated Learning for Robots by Durr, P., Mattiussi, C., Soltoggio, A., Floreano, D.

“…Neuromodulation is thought to be one of the underlying principles of learning and memory in biological neural networks. Recent experiments have shown that…”
Get full text