Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 2007 · 15 citations · 14 references
ComputingComputer ScienceRobotics EngineeringMarkov Decision ProcessesRobot ControlRoboticsKernel MethodsReinforcement LearningRobot NavigationBasis Function ConstructionBasis FunctionsGaussian Basis FunctionsKernel LearningKernel Value Function ApproximationMarkov Decision ModelsMobile Robot NavigationReinforcement Learning For Robotics
The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in a simulated robot arm control and Khepera robot navigation.
14
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Yuhai Wu, Vladimir Vapnik · Technometrics · 1999 · 27K citations
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
A note on two problems in connexion with graphs
E. Dijkstra · Numerische Mathematik · 1959 · 23.8K citations