Loading...
Please wait, while we are loading the content...
Processes using Diffusion Wavelets A Multiscale Framework for Markov Decision Processes using Diffusion Wavelets
| Content Provider | Semantic Scholar |
|---|---|
| Author | Sridhar Mahadevan |
| Copyright Year | 2006 |
| Abstract | We present a novel hierarchical framework for solving Markov decision processes (MDPs) using a multiscale method called diffusion wavelets. Diffusion wavelet bases significantly differ from the Laplacian eigenfunctions studied in the companion paper (Mahadevan and Maggioni, 2006): the basis functions have compact support, and are inherently multi-scale both spectrally and spatially, and capture localized geometric features of the state space, and of functions on it, at different granularities in spacefrequency. Classes of (value) functions that can be compactly represented in diffusion wavelets include piecewise smooth functions. Diffusion wavelets also provide a novel approach to approximate powers of transition matrices. Policy evaluation is usually the expensive step in policy iteration, requiring O(|S|) time to directly solve the Bellman equation (where |S| is the number of states for discrete state spaces or sample size in continuous spaces). Diffusion wavelets compactly represent powers of transition matrices, yielding a direct policy evaluation method requiring only O(|S|) complexity in many cases, which is remarkable because the Green’s function (I − γP ) is usually a full matrix requiring quadratic space just to store each entry. A range of illustrative examples and experiments, from simple discrete MDPs to classic continuous benchmark tasks like inverted pendulum and mountain car, are used to evaluate the proposed framework. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www-all.cs.umass.edu/pubs/2006/maggioni_m_TECH06-36.pdf |
| Alternate Webpage(s) | http://people.cs.umass.edu/~mahadeva/papers/06-36.pdf |
| Alternate Webpage(s) | http://all.cs.umass.edu/pubs/2006/maggioni_m_TECH06-36.pdf |
| Alternate Webpage(s) | http://www.cs.umass.edu/~mahadeva/papers/06-36.pdf |
| Alternate Webpage(s) | http://www-anw.cs.umass.edu/pubs/2006/maggioni_m_TECH06-36.pdf |
| Alternate Webpage(s) | http://www.math.duke.edu/~mauro/Papers/RPI_Multiscale_TechRep.pdf |
| Alternate Webpage(s) | http://www.researchgate.net/profile/Mauro_Maggioni/publication/228352560_A_multiscale_framework_for_Markov_decision_processes_using_diffusion_wavelets/links/5416def30cf2788c4b35ef79.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
