Revisiting Risk-Sensitive MDPs: New Algorithms and Results

@inproceedings{Hou2014RevisitingRM,
  title={Revisiting Risk-Sensitive MDPs: New Algorithms and Results},
  author={Ping Hou and William Yeoh and Pradeep Varakantham},
  booktitle={ICAPS},
  year={2014}
}
While Markov Decision Processes (MDPs) have been shown to be effective models for planning under uncertainty, the objective to minimize the expected cumulative cost is inappropriate for high-stake planning problems. As such, Yu, Lin, and Yan (1998) introduced the Risk-Sensitive MDP (RSMDP) model, where the objective is to find a policy that maximizes the probability that the cumulative cost is within some user-defined cost threshold. In this paper, we revisit this problem and introduce new… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 17 CITATIONS

Similar Papers

Loading similar papers…