Measuring Structural Similarities in Finite MDPs

@inproceedings{Wang2019MeasuringSS,
  title={Measuring Structural Similarities in Finite MDPs},
  author={H. Wang and Shaokang Dong and Ling Shao},
  booktitle={IJCAI},
  year={2019}
}
In this paper, we investigate the structural similarities within a finite Markov decision process (MDP). We view a finite MDP as a heterogeneous directed bipartite graph and propose novel measures for the state and action similarities, in a mutually reinforced manner. We prove that the state similarity is a metric and the action similarity is a pseudometric. We also establish the connection between the proposed similarity measures and the optimal values of the MDP. Extensive experiments show… Expand
5 Citations
Privacy-preserving spatial keyword location-to-trajectory matching
An efficient algorithm for spatio-textual location matching
MULTIPOLAR: MULTI-SOURCE POLICY AGGREGA-
  • PDF
CAPMAN: Cooling and Active Power Management in big.LITTLE Battery Supported Devices
  • J. Zhou, Zichen Xu, Wenli Zheng, Yuhao Wang
  • Computer Science
  • 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)
  • 2020
  • 1

References

SHOWING 1-10 OF 37 REFERENCES
Metrics for Finite Markov Decision Processes
  • 171
  • Highly Influential
  • PDF
Measuring the Distance Between Finite Markov Decision Processes
  • 32
  • PDF
P-Rank: a comprehensive structural similarity measure over information networks
  • 197
  • PDF
SimRank: a measure of structural-context similarity
  • 1,803
  • Highly Influential
  • PDF
Scalable and axiomatic ranking of network role similarity
  • 19
  • PDF
Equivalence notions and model minimization in Markov decision processes
  • 281
  • PDF
Towards a Unified Theory of State Abstraction for MDPs
  • 288
  • PDF
SimFusion: measuring similarity using unified relationship matrix
  • 128
  • PDF
MatchSim: a novel similarity measure based on maximum neighborhood matching
  • 44
...
1
2
3
4
...