Approximate Kalman Filter Q-Learning for Continuous State-Space MDPs

09/26/2013
by   Charles Tripp, et al.
0

We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the mean Bellman residual. Our algorithm uses a Kalman filter model to estimate those weights and we have developed a simpler approximate Kalman filter model that outperforms the current state of the art projected TD-Learning methods on several standard benchmark problems.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset