Agnostic System Identification for Model-Based Reinforcement Learning

  title={Agnostic System Identification for Model-Based Reinforcement Learning},
  author={St{\'e}phane Ross and J. Andrew Bagnell},
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 nearoptimal policy… CONTINUE READING
Highly Cited
This paper has 66 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 1 time over the past 90 days. VIEW TWEETS


Publications citing this paper.

66 Citations

Citations per Year
Semantic Scholar estimates that this publication has 66 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…