Value-directed Compression of POMDPs

Value-directed Compression of POMDPs (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Pascal Poupart , Craig Boutilier

Venue:	In NIPS 15
Citations:	59 - 4 self

BibTeX

@INPROCEEDINGS{Poupart02value-directedcompression,
    author = {Pascal Poupart and Craig Boutilier},
    title = {Value-directed Compression of POMDPs},
    booktitle = {In NIPS 15},
    year = {2002},
    pages = {1547--1554},
    publisher = {MIT Press}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We examine the problem of generating state-space compressions of POMDPs in a way that minimally impacts decision quality. We analyze the impact of compressions on decision quality, observing that compressions that allow accurate policy evaluation (prediction of expected future reward) will not affect decision quality.

Citations

1075	Iterative Methods for Sparse Linear Systems - Saad - 1996
330	The Information Bottleneck Method - Tishby, Pereira, et al. - 1999
146	SPUDD: Stochastic planning using decision diagrams - Hoey, St-Aubin, et al. - 1999
120	Stochastic dynamic programming with factored representations - Boutilier, Dearden, et al.
94	Computing optimal policies for partially observable decision processes using compact representations - Boutilier, Poole - 1996
88	Memoryless policies: Theoretical limitations and practical results. In From Animals to Animats 3 - Littman - 1994
78	Equivalence notions and model minimization in markov decision processes - Givan, Dean, et al. - 2003
58	Max-norm projections for factored MDPs - Guestrin, Koller, et al. - 2001
31	Hidden state and reinforcement learning with instancebased state identification - McCallum - 2002
26	Direct valueapproximation for factored MDPs - Schuurmans, Patrascu - 2001
24	Greedy linear value-approximation for factored markov decision processes - Patrascu, Poupart, et al. - 2002
21	Solving factored POMDPs with linear value functions. IJCAI-01 workshop on Planning under Uncertainty and Incomplete Information - Guestrin, Koller, et al. - 2001
18	Greedy linear value function approximation for factored markov decision processes - Patrascu, Poupart, et al. - 2002
14	A survey of POMDP solution techniques - Murphy - 2000
9	separability and temporal probabilistic models - Sufficiency - 2001
2	Information-theoretic features for reinforcement learning. Unpublished manuscript - Guestrin, Ormoneit