Min Max Generalization for Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes

Details Min Max Generalization for Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes Min Max Generalization for Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes

2012-02-23

arxiv.org/abs/1202.5298v1

Computer Science

Systems and Control

Scientific paper

We study the minmax optimization problem introduced in [22] for computing policies for batch mode reinforcement learning in a deterministic setting. First, we show that this problem is NP-hard. In the two-stage case, we provide two relaxation schemes. The first relaxation scheme works by dropping some constraints in order to obtain a problem that is solvable in polynomial time. The second relaxation scheme, based on a Lagrangian relaxation where all constraints are dualized, leads to a conic quadratic programming problem. We also theoretically prove and empirically illustrate that both relaxation schemes provide better results than those given in [22].

Affiliated with

Also associated with

No associations

Rating

Min Max Generalization for Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes 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 Min Max Generalization for Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Min Max Generalization for Deterministic Batch Mode Reinforcement Learning: Relaxation Schemes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-77550