2017

Practical Learning of Predictive State Representations

Downey, Carlton, Hefny, Ahmed, Gordon, Geoffrey

Understand

Over the past decade there has been considerable interest in spectral algorithms for learning Predictive State Representations (PSRs).

  • Spectral algorithms have appealing theoretical guarantees; however, the resulting models do not always perform well on inference tasks in practice.
  • One reason for this behavior is the mismatch between the intended task (accurate filtering or prediction) and the loss function being optimized by the algorithm (estimation error in model parameters).
  • A natural idea is to improve performance by refining PSRs using an algorithm such as EM.

Built on

  • On the convergence properties of the em algorithm

    Wu, C. F. Jeff · 1983

    Earlier work this paper cites.

  • Observable operator models for discrete stochastic time series

    Jaeger, Herbert · 1999

    Earlier work this paper cites.

  • Predictive representations of state

    Littman, Michael L., Sutton, Richard S., and Singh, Satinder · 2001

    Earlier work this paper cites.

  • Predictive state representations: A new theory for modeling dynamical systems

    Singh, Satinder, James, Michael R., and Rudary, Matthew R · 2004

    Earlier work this paper cites.

  • Closing the learning-planning loop with predictive state representations

    Original

    Boots, Byron, Siddiqi, Sajid M., and Gordon, Geoffrey J · 2009

    Earlier work this paper cites.

Similar

  • Learning nonlinear dynamic models

    Original

    Langford, John, Salakhutdinov, Ruslan, and Zhang, Tong · 2009

    Cited alongside, same era.

  • Predictive state temporal difference learning

    Original

    Boots, Byron and Gordon, Geoffrey J · 2010

    Cited alongside, same era.

  • Learning message-passing inference machines for structured prediction

    Ross, Stéphane, Munoz, Daniel, Hebert, Martial, and Bagnell, J. Andrew · 2011

    Cited alongside, same era.

  • Supervised learning for dynamical system learning

    Hefny, Ahmed, Downey, Carlton, and Gordon, Geoffrey J · 2015

    Cited alongside, same era.

Then

  • Learning latent variable models by improving spectral solutions with exterior point methods

    Shaban, Amirreza, Farajtabar, Mehrdad, Xie, Bo, Song, Le, and Boots, Byron · 2015

    Later among the works it cites.

  • Improving predictive state representations via gradient descent

    Jiang, Nan, Kulesza, Alex, and Singh, Satinder P · 2016

    Later among the works it cites.

  • Learning to filter with predictive state inference machines

    Sun, Wen, Venkatraman, Arun, Boots, Byron, and Bagnell, J. Andrew · 2016

    Later among the works it cites.

  • Online instrumental variable regression with applications to online linear system identification

    Venkatraman, Arun, Sun, Wen, Hebert , Martial, Bagnell, J. Andrew (Drew), and Boots, Byron · 2016

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…