Empirical Dynamic Programming

Empirical Dynamic Programming

We propose empirical dynamic programming algorithms for Markov decision processes (MDPs). In these algorithms, the exact expectation in the Bellman operator in classical value iteration is replaced by an empirical estimate to get ‘empirical value iteration’ (EVI). Policy evaluation and policy improvement in classical policy iteration are also replaced by simulation to get ‘empirical policy iter...

An Empirical Dynamic Programming Algorithm for Continuous MDPs

We propose universal randomized function approximation-based empirical value iteration (EVI) algorithms for Markov decision processes. The ‘empirical’ nature comes from each iteration being done empirically from samples available from simulations of the next state. This makes the Bellman operator a random operator. A parametric and a non-parametric method for function approximation using a para...

Modern Computational Applications of Dynamic Programming

Computational dynamic programming, while of some use for situations typically encountered in industrial and systems engineering, has proved to be of much greater significance in many areas of computer science. We review some of these applications here.

statistical inference via empirical bayes approach for stationary and dynamic contingency tables

چکیده ندارد.

Empirical study on extreme programming