Risk-Sensitive Markov Decision Process with Limited Budget

  title={Risk-Sensitive Markov Decision Process with Limited Budget},
  author={Daniel Augusto de Melo Moreira and Karina Valdivia Delgado and Leliane Nunes de Barros},
  journal={2017 Brazilian Conference on Intelligent Systems (BRACIS)},
Markov Decision Process (MDP) commonly have the objective of finding a policy that minimizes the expected cumulative cost. Although this optimization criterion is useful, some policy executions may result in a too high cost, which for some applications is unacceptable (e.g. policies for military operations). A better optimization problem for those applications is based on probability maximization of cumulative costs within a threshold, called Risk-Sensitive MDP (RS-MDP). In the frame of RS-MDP… CONTINUE READING
Highly Cited
This paper has 93 citations. REVIEW CITATIONS

4 Figures & Tables



Citations per Year

93 Citations

Semantic Scholar estimates that this publication has 93 citations based on the available data.

See our FAQ for additional information.