Percentile Optimization for Markov Decision Processes with Parameter Uncertainty

  title={Percentile Optimization for Markov Decision Processes with Parameter Uncertainty},
  author={Erick Delage and Shie Mannor},
  journal={Operations Research},
Markov decision processes are an effective tool in modeling decision-making in uncertain dynamic environments. Since the parameters of these models are typically estimated from data or learned from experience, it is not surprising that the actual performance of a chosen strategy often significan tly differs from the designer’s initial expectations due to unavoidable modeling ambiguity. In this paper, we present a set of percentile criteria that are conceptually natural an d representative of… CONTINUE READING
Highly Cited
This paper has 131 citations. REVIEW CITATIONS

4 Figures & Tables



Citations per Year

132 Citations

Semantic Scholar estimates that this publication has 132 citations based on the available data.

See our FAQ for additional information.