LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method

Photo from wikipedia

In this paper, we provide two new stable online algorithms for the problem of prediction in reinforcement learning, i.e., estimating the value function of a model-free Markov reward process using… Click to show full abstract

In this paper, we provide two new stable online algorithms for the problem of prediction in reinforcement learning, i.e., estimating the value function of a model-free Markov reward process using the linear function approximation architecture and with memory and computation costs scaling quadratically in the size of the feature set. The algorithms employ the multi-timescale stochastic approximation variant of the very popular cross entropy optimization method which is a model based search method to find the global optimum of a real-valued function. A proof of convergence of the algorithms using the ODE method is provided. We supplement our theoretical results with experimental comparisons. The algorithms achieve good performance fairly consistently on many RL benchmark problems with regards to computational efficiency, accuracy and stability.

Keywords: function approximation; method; reinforcement learning; function; linear function

Journal Title: Machine Learning
Year Published: 2018

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.