papers AI Learner
The Github is limit! Click to go to the new site.

An Online Prediction Algorithm for Reinforcement Learning with Linear Function Approximation using Cross Entropy Method

2018-06-15
Ajin George Joseph, Shalabh Bhatnagar

Abstract

In this paper, we provide two new stable online algorithms for the problem of prediction in reinforcement learning, \emph{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 (CE) 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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1806.06720

PDF

https://arxiv.org/pdf/1806.06720


Similar Posts

Comments