My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
Abstract— Groups of reinforcement learning agents interacting in a common environment often fail to learn optimal behaviors. Poor performance is particularly common in environmen...
Although necessary, learning to discover new solutions is often long and difficult, even for supposedly simple tasks such as counting. On the other hand, learning by imitation pr...
Abstract— One of the major challenges in both action generation for robotics and in the understanding of human motor control is to learn the “building blocks of movement genera...
A teaching methodology called Imitative-Reinforcement-Corrective (IRC) learning is described, and proposed as a general approach for teaching embodied non-linguistic AGI systems. I...
Ben Goertzel, Cassio Pennachin, Nil Geisweiller, M...