The Infinite Partially Observable Markov Decision Process

@inproceedings{DoshiVelez2009TheIP,
  title={The Infinite Partially Observable Markov Decision Process},
  author={Finale Doshi-Velez},
  booktitle={NIPS},
  year={2009}
}
The Partially Observable Markov Decision Process (POMDP) framework has proven useful in planning domains where agents must balance actions that provide knowledge and actions that provide reward. Unfortunately, most POMDPs are complex structures with a large number of parameters. In many real-world problems, both the structure and the parameters are difficult to specify from domain knowledge alone. Recent work in Bayesian reinforcement learning has made headway in learning POMDP models; however… CONTINUE READING
Highly Cited
This paper has 85 citations. REVIEW CITATIONS

5 Figures & Tables

Topics

Statistics

01020201020112012201320142015201620172018
Citations per Year

85 Citations

Semantic Scholar estimates that this publication has 85 citations based on the available data.

See our FAQ for additional information.