Nonapproximability Results for Partially Observable Markov Decision Processes

  title={Nonapproximability Results for Partially Observable Markov Decision Processes},
  author={Judy Goldsmith and Christopher Lusena and Martin Mundhenk},
  journal={J. Artif. Intell. Res.},
We show that for several variations of partially observable Markov decision processes, polynomial-time algorithms for nding control policies are unlikely to or simply don't have guarantees of nding policies within a constant factor or a constant summand of optimal. Here \unlikely" means \unless some complexity classes collapse," where the collapses considered are P = NP, P = PSPACE, or P = EXP. Until or unless these collapses are shown to hold, any control-policy designer must choose between… CONTINUE READING
Highly Cited
This paper has 98 citations. REVIEW CITATIONS
60 Citations
32 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 60 extracted citations

99 Citations

Citations per Year
Semantic Scholar estimates that this publication has 99 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…