An Online Spectral Learning Algorithm for Partially Observable Nonlinear Dynamical Systems

Recently, a number of researchers have proposed spectral algorithms for learning models of dynamical systems—for example, Hidden Markov Models (HMMs), Partially Observable Markov Decision Processes (POMDPs), and Transformed Predictive State Representations (TPSRs). These algorithms are attractive since they are statistically consistent and not subject to local optima. However, they are batch methods: they need to store their entire training data set in memory at once and operate on it as a large matrix, and so they cannot scale to extremely large data sets (either many examples or many features per example). In turn, this restriction limits their ability to learn accurate models of complex systems. To overcome these limitations, we propose a new online spectral algorithm, which uses tricks such as incremental Singular Value Decomposition (SVD) and random projections to scale to much larger data sets and more complex systems than previous methods. We demonstrate the new method on an ...

• Type: Journal
• Year: 2011
• Where: AAAI
• Authors: Byron Boots, Geoffrey J. Gordon
• Keywords: AAAI 2011, Intelligent Agents, Observable Markov Decision, Singular Value Decomposition, Singular Value Decomposition Svd