Accession Number ADA566112
Title Spectral Approaches to Learning Predictive Representations.
Publication Date Sep 2012
Media Count 177p
Personal Author B. Boots
Abstract A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must obtain an accurate environment model, and then plan to maximize reward. However, for complex domains, specifying a model by hand can be a time- consuming process. This motivates an alternative approach: learning a model directly from observations. Unfortunately, learning algorithms often recover a model that is too inaccurate to support planning or too large and complex for planning to succeed; or, they require excessive prior domain knowledge or fail to provide guarantees such as statistical consistency. To address this gap, we propose spectral subspace identification algorithms which provably learn compact, accurate, predictive models of partially observable dynamical systems directly from sequences of action-observation pairs. Our research agenda includes several variations of this general approach: spectral methods for classical models like Kalman filters and hidden Markov models, batch algorithms and online algorithms, and kernel-based algorithms for learning models in high- and infinite-dimensional feature spaces. All of these approaches share a common framework: the model's belief space is represented as predictions of observable quantities and spectral algorithms are applied to learn the model parameters. Unlike the popular EM algorithm, spectral learning algorithms are statistically consistent, computationally efficient, and easy to implement using established matrix-algebra techniques. We evaluate our learning algorithms on a series of prediction and planning tasks involving simulated data and real robotic systems.
Keywords Accuracy
Algorithms
Artificial intelligence
Bayes theorem
Computerized simulation
Hilbert space
Identification algorithms
Kalman filtering
Learning machines
Markov processes
Mathematical prediction
Observation
Predictive state representations
Robotics
Robots
Spectral learning algorithms
Theses
Uncertainty


 
Source Agency Non Paid ADAS
NTIS Subject Category 72B - Algebra, Analysis, Geometry, & Mathematical Logic
72F - Statistical Analysis
62 - Computers, Control & Information Theory
Corporate Author Carnegie-Mellon Univ., Pittsburgh, PA. School of Computer Science.
Document Type Thesis
Title Note Doctoral thesis.
NTIS Issue Number 1306
Contract Number N00014-09-1-1052

Science and Technology Highlights

See a sampling of the latest scientific, technical and engineering information from NTIS in the NTIS Technical Reports Newsletter

Acrobat Reader Mobile    Acrobat Reader