Adaptive Bases for Reinforcement Learning

Details Adaptive Bases for Reinforcement Learning Adaptive Bases for Reinforcement Learning

2010-05-02

arxiv.org/abs/1005.0125v1

Computer Science

Learning

Scientific paper

We consider the problem of reinforcement learning using function approximation, where the approximating basis can change dynamically while interacting with the environment. A motivation for such an approach is maximizing the value function fitness to the problem faced. Three errors are considered: approximation square error, Bellman residual, and projected Bellman residual. Algorithms under the actor-critic framework are presented, and shown to converge. The advantage of such an adaptive basis is demonstrated in simulations.

Affiliated with

Also associated with

No associations

Rating

Adaptive Bases for Reinforcement Learning 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 Adaptive Bases for Reinforcement Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive Bases for Reinforcement Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-723845