Learning on real robots in an real, unaltered environment provides an extremely challenging problem. Many of the simplifying assumptions made in other areas of learning cannot be ...
Computer models can be used to investigate the role of emotion in learning. Here we present EARL, our framework for the systematic study of the relation between emotion, adaptation...
— This paper presents a new reinforcement learning algorithm for accelerating acquisition of new skills by real mobile robots, without requiring simulation. It speeds up Q-learni...
Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high...
— Accurate and fast control of wheel speeds in the presence of noise and nonlinearities is one of the crucial requirements for building fast mobile robots, as they are required i...