Combining dynamic abstractions in large MDPs
One of the reasons that it is difficult to plan and act in real-worlddomains is that they are very large. Existing research generallydeals with the large domain size using a static representation andexploiting a single type of domain structure. In this paper, wecreate a framework that encapsulates...
Main Authors: | Steinkraus, Kurt, Kaelbling, Leslie Pack |
---|---|
Language: | en_US |
Published: |
2005
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/30496 |
Similar Items
-
Spatial and Temporal Abstractions in POMDPs Applied to Robot Navigation
by: Theocharous, Georgios, et al.
Published: (2005) -
Adaptive Envelope MDPs for Relational Equivalence-based Planning
by: Gardiol, Natalia H., et al.
Published: (2008) -
Solving large stochastic planning problems using multiple dynamic abstractions
by: Steinkraus, Kurt Alan, 1978-
Published: (2006) -
Batch-iFDD for representation expansion in large MDPs
by: Geramifard, Alborz, et al.
Published: (2015) -
Learning object segmentation from video data
by: Ross, Michael G., et al.
Published: (2005)