Reinforcement Learning with Linear Function Approximation and LQ control Converges

Details Reinforcement Learning with Linear Function Approximation and LQ control Converges Reinforcement Learning with Linear Function Approximation and LQ control Converges

2003-06-22

arxiv.org/abs/cs/0306120v2

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.

Affiliated with

Also associated with

No associations

Rating

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.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-154114