Date of Original Version
Abstract or Description
Many control problems in the robotics field can be cast as Partially Observed Markovian Decision Problems (POMDPs), an optimal control formalism. Finding optimal solutions to such problems in general, however is known to be intractable. It has often been observed that in practice, simple structured controllers suffice for good sub-optimal control, and recent research in the artificial intelligence community has focused on policy search methods as techniques for finding sub-optimal controllers when such structured controllers do exist. Traditional model-based reinforcement learning algorithms make a certainty equivalence assumption on their learned models and calculate optimal policies for a maximum-likelihood Markovian model. In this work, we consider algorithms that evaluate and synthesize controllers under distributions of Markovian models. Previous work has demonstrated that algorithms that maximize mean reward with respect to model uncertainty leads to safer and more robust controllers. We consider briefy other performance criterion that emphasize robustness and exploration in the search for controllers, and note the relation with experiment design and active learning. To validate the power of the approach on a robotic application we demonstrate the presented learning control algorithm by flying an autonomous helicopter. We show that the controller learned is robust and delivers good performance in this real-world domain.