2012
Bouvrie, Jake; Maggioni, Mauro
Efficient Solution of Markov Decision Problems with Multiscale Representations Proceedings Article
In: Proc. 50th Annual Allerton Conference on Communication, Control, and Computing, 2012.
BibTeX | Tags: Machine learning, reinforcement learning, representation learning
@inproceedings{BM_EfficientMultiscaleMarkov,
title = {Efficient Solution of Markov Decision Problems with Multiscale Representations},
author = {Jake Bouvrie and Mauro Maggioni},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. 50th Annual Allerton Conference on Communication, Control, and Computing},
keywords = {Machine learning, reinforcement learning, representation learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Bouvrie, Jake; Maggioni, Mauro
Multiscale Markov Decision Problems: Compression, Solution, and Transfer Learning Journal Article
In: 2012.
Links | BibTeX | Tags: Machine learning, multiscale analysis, reinforcement learning, representation learning, spectral graph theory, transfer learning
@article{BM:MMDPs,
title = {Multiscale Markov Decision Problems: Compression, Solution, and Transfer Learning},
author = {Jake Bouvrie and Mauro Maggioni},
url = {http://arxiv.org/abs/1212.1143},
year = {2012},
date = {2012-01-01},
keywords = {Machine learning, multiscale analysis, reinforcement learning, representation learning, spectral graph theory, transfer learning},
pubstate = {published},
tppubtype = {article}
}
2007
Mahadevan, Sridhar; Maggioni, Mauro
Proto-value Functions: A Spectral Framework for Solving Markov Decision Processes Journal Article
In: JMLR, vol. 8, pp. 2169–2231, 2007.
BibTeX | Tags: diffusion geometry, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory
@article{smmm:jmrl1,
title = {Proto-value Functions: A Spectral Framework for Solving Markov Decision Processes},
author = {Sridhar Mahadevan and Mauro Maggioni},
year = {2007},
date = {2007-01-01},
journal = {JMLR},
volume = {8},
pages = {2169--2231},
keywords = {diffusion geometry, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory},
pubstate = {published},
tppubtype = {article}
}
2006
Maggioni, Mauro; Mahadevan, Sridhar
Fast Direct Policy Evaluation using Multiscale Analysis of Markov Diffusion Processes Proceedings Article
In: ICML 2006, pp. 601–608, 2006.
BibTeX | Tags: diffusion geometry, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory
@inproceedings{smmm:FastDirectMDP,
title = {Fast Direct Policy Evaluation using Multiscale Analysis of Markov Diffusion Processes},
author = {Mauro Maggioni and Sridhar Mahadevan},
year = {2006},
date = {2006-01-01},
booktitle = {ICML 2006},
pages = {601--608},
keywords = {diffusion geometry, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory},
pubstate = {published},
tppubtype = {inproceedings}
}
Mahadevan, Sridhar; Ferguson, Kim; Osentoski, Sarah; Maggioni, Mauro
Simultaneous Learning of Representation and Control In Continuous Domains Proceedings Article
In: AAAI, AAAI Press, 2006.
BibTeX | Tags: diffusion geometry, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory
@inproceedings{smkfsomm:SimLearningReprControlContinuous,
title = {Simultaneous Learning of Representation and Control In Continuous Domains},
author = {Sridhar Mahadevan and Kim Ferguson and Sarah Osentoski and Mauro Maggioni},
year = {2006},
date = {2006-01-01},
booktitle = {AAAI},
publisher = {AAAI Press},
keywords = {diffusion geometry, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory},
pubstate = {published},
tppubtype = {inproceedings}
}
2005
Mahadevan, Sridhar; Maggioni, Mauro
Value Function Approximation with Diffusion Wavelets and Laplacian Eigenfunctions Proceedings Article
In: University of Massachusetts, Department of Computer Science Technical Report TR-2005-38; Proc. NIPS 2005, 2005.
BibTeX | Tags: diffusion geometry, diffusion wavelets, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory
@inproceedings{smmm:ValueFunction,
title = {Value Function Approximation with Diffusion Wavelets and Laplacian Eigenfunctions},
author = {Sridhar Mahadevan and Mauro Maggioni},
year = {2005},
date = {2005-01-01},
booktitle = {University of Massachusetts, Department of Computer Science Technical Report TR-2005-38; Proc. NIPS 2005},
keywords = {diffusion geometry, diffusion wavelets, Laplacian eigenfunctions, Machine learning, Manifold Learning, random walks, reinforcement learning, representation learning, spectral graph theory},
pubstate = {published},
tppubtype = {inproceedings}
}
- Lectures at Summer School at Peking University, July 2017.
- PCMI Lectures, Summer 2016: Lecture 1, Lecture 2, Problems/discussion points
- Google Scholar
- Papers on the ArXiv
- Papers on MathsciNet
- Tutorials on diffusion geometry and multiscale analysis on graphs at the MRA Internet Program at IPAM: Part I and Part II.
- Diffusion Geometries, Diffusion Wavelets and Harmonic Analysis of large data sets, IPAM, Multiscale Geometric Analysis Program, Fall 2004.
- Diffusion Geometries, global and multiscale, IPAM, 2005.