Corpus ID: 10922274

Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes

@article{Montfar2015GeometryAD,
  title={Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes},
  author={Guido Mont{\'u}far and Keyan Zahedi and Nihat Ay},
  journal={ArXiv},
  year={2015},
  volume={abs/1503.07206}
}
  • Guido Montúfar, Keyan Zahedi, Nihat Ay
  • Published 2015
  • Computer Science, Mathematics
  • ArXiv
  • It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies are generally stochastic. We study the expected reward optimization problem over the set of memoryless stochastic policies. We formulate this as a constrained linear optimization problem and develop a corresponding geometric framework. We show that any POMDP… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    Infinite-Horizon Policy-Gradient Estimation

    VIEW 2 EXCERPTS

    Reinforcement Learning: An Introduction

    VIEW 1 EXCERPT