Constrained Control of Large Graph-based MDPs Under Measurement Uncertainty

@article{haksar_constrained_2020,
  title = {Constrained {Control} of {Large} {Graph}-based {MDPs} {Under} {Measurement} {Uncertainty}},
  abstract = {We consider controlling a graph-based Markov decision process (GMDP) with a control capacity constraint given only uncertain measurements of the underlying state. We also consider two special structural properties of GMDPs, called Anonymous Influence and Symmetry. Large-scale spatial processes such as forest wildfires, disease epidemics, opinion dynamics, and robot swarms are well-modeled by GMDPs with these properties. We adopt a certainty-equivalence approach and derive efficient and scalable algorithms for estimating the GMDP state given uncertain measurements, and for computing approximately optimal control policies given a maximumlikelihood state estimate. We also derive sub-optimality bounds for our estimation and control algorithms. Unlike prior work, our methods scale to GMDPs with large state-spaces and explicitly enforce a control constraint. We demonstrate the effectiveness of our estimation and control approach in simulations of controlling a forest wildfire using a model with 10{\textasciicircum}\{1192\} total states.},
  language = {en},
  journal = {IEEE Transactions on Automatic Control},
  author = {Haksar, Ravi N. and Schwager, Mac},
  year = {2020},
  note = {Under review}
}