Computer Science – Learning
Scientific paper
2003-06-22
Computer Science
Learning
9 pages
Scientific paper
Reinforcement learning is commonly used with function approximation. However, very few positive results are known about the convergence of function approximation based RL control algorithms. In this paper we show that TD(0) and Sarsa(0) with linear function approximation is convergent for a simple class of problems, where the system is linear and the costs are quadratic (the LQ control problem). Furthermore, we show that for systems with Gaussian noise and non-completely observable states (the LQG problem), the mentioned RL algorithms are still convergent, if they are combined with Kalman filtering.
Lorincz Andras
Szita Istvan
No associations
LandOfFree
Reinforcement Learning with Linear Function Approximation and LQ control Converges does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Reinforcement Learning with Linear Function Approximation and LQ control Converges, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Reinforcement Learning with Linear Function Approximation and LQ control Converges will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-154114