ar X iv : 1 21 1 . 59 01 v 1 [ st at . M L ] 2 6 N ov 2 01 2 BAYESIAN LEARNING OF NOISY MARKOV DECISION PROCESSES

نویسنده

  • NICK WHITELEY
چکیده

We consider the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, which is shown to be essential for good convergence properties of the MCMC sampler. As an illustration, the method is applied to learning a human controller.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

ar X iv : 1 61 1 . 01 90 0 v 1 [ st at . M L ] 7 N ov 2 01 6 Optimal rates for the regularized learning algorithms under general source condition

We consider the learning algorithms under general source condition with the polynomial decay of the eigenvalues of the integral operator in vector-valued function setting. We discuss the upper convergence rates of Tikhonov regularizer under general source condition corresponding to increasing monotone index function. The convergence issues are studied for general regularization schemes by using...

متن کامل

ar X iv : 1 41 1 . 08 35 v 1 [ cs . L O ] 4 N ov 2 01 4 Variations on the Stochastic Shortest Path Problem ⋆

In this invited contribution, we revisit the stochastic shortest path problem, and show how recent results allow one to improve over the classical solutions: we present algorithms to synthesize strategies with multiple guarantees on the distribution of the length of paths reaching a given target, rather than simply minimizing its expected value. The concepts and algorithms that we propose here ...

متن کامل

ar X iv : h ep - l at / 0 01 10 26 v 2 1 3 N ov 2 00 0 1 QCD vacuum structure

Several issues related to the structure of the QCD vacuum are reviewed. We concentrate mostly on results concerning instantons and center vortices.

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012