Searched for: department%3A%22Biomechanical%255C%252BEngineering%22
(1 - 2 of 2)
document
Schuitema, E. (author), Caarls, W. (author), Wisse, M. (author), Jonker, P.P. (author), Babuska, R. (author)
Reinforcement Learning is a promising paradigm for adding learning capabilities to humanoid robots. One of the difficulties of the real world is the presence of disturbances. In Reinforcement Learning, disturbances are typically dealt with stochastically. However, large and infrequent disturbances do not fit well in this framework; essentially,...
conference paper 2010
document
Van Vliet, B. (author), Caarls, W. (author), Schuitema, E. (author), Jonker, P.P. (author)
Reinforcement learning is a way to learn control tasks by trial and error. Even for simple motor control tasks, however, this can take a long time. We can speed up learning by using prior knowledge, but this is not always available, especially for an autonomous agent. One way to add limited prior knowledge is to use subgoals, defining points...
conference paper 2011