Department of Computer Science
A novel orthogonal NMF-based belief compression for POMDPs
High dimensionality of POMDP's belief state space is one major cause that makes the underlying optimal policy computation intractable. Belief compression refers to the methodology that projects the belief state space to a low-dimensional one to alleviate the problem. In this paper, we propose a novel orthogonal non-negative matrix factorization (O-NMF) for the projection. The proposed O-NMF not only factors the belief state space by minimizing the reconstruction error, but also allows the compressed POMDP formulation to be efficiently computed (due to its orthogonality) in a value-directed manner so that the value function will take same values for corresponding belief states in the original and compressed state spaces. We have tested the proposed approach using a number of benchmark problems and the empirical results confirms its effectiveness in achieving substantial computational cost saving in policy computation.
Source Publication Title
Proceedings of the 24th international conference on Machine learning (ICML'07)
Ghahramani, Zoubin ; ACM Digital Library
Corvalis, United States
Copyright 2007 by the author(s)/ owner(s)
This work has been partially supported by RGC Central Allocation Group Research Grant (HKBU 2/03/C) and HKBU Faculty Research Grant (FRG/05-06/II-81).
Link to Publisher's Edition
Li, X., Cheung, W., Liu, J., & Wu, Z. (2007). A novel orthogonal NMF-based belief compression for POMDPs. Proceedings of the 24th international conference on Machine learning (ICML'07), 537-544. https://doi.org/10.1145/1273496.1273564