Agnostic System Identification for Model-Based Reinforcement Learning

Details Agnostic System Identification for Model-Based Reinforcement Learning Agnostic System Identification for Model-Based Reinforcement Learning

2012-03-05

arxiv.org/abs/1203.1007v1

Computer Science

Learning

17 pages

Scientific paper

A fundamental problem in control is to learn a model of a system from observations that is useful for controller synthesis. To provide good performance guarantees, existing methods must assume that the real system is in the class of models considered during learning. We present an iterative method with strong guarantees even in the agnostic case where the system is not in the class. In particular, we show that any no-regret online learning algorithm can be used to obtain a near-optimal policy, provided some model achieves low training error and access to a good exploration distribution. Our approach applies to both discrete and continuous domains. We demonstrate its efficacy and scalability on a challenging helicopter domain from the literature.

Affiliated with

Also associated with

No associations

Rating

Agnostic System Identification for Model-Based 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 Agnostic System Identification for Model-Based Reinforcement Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Agnostic System Identification for Model-Based Reinforcement Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-134033