On the Numeric Stability of Gaussian Processes Regression for Relational Reinforcement Learning
نویسنده
چکیده
In this work we investigate the behavior of Gaussian processes as a regression technique for reinforcement learning. When confronted with too many mutually dependant learning examples, the matrix inversion needed for prediction of a new target value becomes numerically unstable. By paying attention to using suitable numerical techniques and employing QR-factorization these instabilities can be avoided. This leads to better and more stable performance of the attached reinforcement learner.
منابع مشابه
Combining Model - Based and Instance - Based Learning for First Order Regression ( Extended Abstract )
With the development of relational reinforcement learning [5, 4] came the need for incremental relational regression algorithms. A relational regression algorithm generalizes over learning examples with a continuous target value and makes predictions about the value of unseen examples, using a relational representation for both the learning examples and the resulting function. A number of these...
متن کاملGaussian Processes in Reinforcement Learning
We exploit some useful properties of Gaussian process (GP) regression models for reinforcement learning in continuous state spaces and discrete time. We demonstrate how the GP model allows evaluation of the value function in closed form. The resulting policy iteration algorithm is demonstrated on a simple problem with a two dimensional state space. Further, we speculate that the intrinsic abili...
متن کاملOptimal Reinforcement Learning for Gaussian Systems
The exploration-exploitation tradeoff is among the central challenges of reinforcement learning. A hypothetical exact Bayesian learner would provide the optimal solution, but is intractable in general. I show that, however, in the specific case of Gaussian process inference, it is possible to make analytic statements about optimal learning of both rewards and transition dynamics, for nonlinear,...
متن کاملReinforcement Learning Based PID Control of Wind Energy Conversion Systems
In this paper an adaptive PID controller for Wind Energy Conversion Systems (WECS) has been developed. Theadaptation technique applied to this controller is based on Reinforcement Learning (RL) theory. Nonlinearcharacteristics of wind variations as plant input, wind turbine structure and generator operational behaviordemand for high quality adaptive controller to ensure both robust stability an...
متن کاملRelational Reinforcement Learning
Reinforcement learning [10] is a subtopic of machine learning that is concerned with software systems that learn to behave through interaction with their environment and receive only feedback on the quality of their current behavior instead of a set of correctly labelled learning examples. Although reinforcement learning algorithms have been studied extensively in a propositional setting, their...
متن کامل