By Topic

Policy-Gradient Based Actor-Critic Algorithms

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Awate, Y.P. ; marketRx - A Cognizant Co., Gurgaon, India

We consider the framework of a set of recently proposed two-timescale actor-critic algorithms for reinforcement-learning using the long-run average-reward criterion and linear feature-based value-function approximation. The actor update is based on the stochastic policy-gradient ascent rule. We derive a stochastic-gradient-based novel critic update to minimize the variance of the policy-gradient estimator used in the actor update. We propose a novel baseline structure for variance minimization of an estimator and derive an optimal baseline which makes the covariance matrix a zero matrix - the best achievable. We derive a novel actor update based on the optimal baseline deduced for an existing algorithm. We derive another novel actor update using the optimal baseline for an unbiased policy-gradient estimator which we deduce from the Policy-Gradient Theorem with Function Approximation. The computational results demonstrate that the proposed algorithms outperform the state-of-the-art on Garnet problems.

Published in:

Intelligent Systems, 2009. GCIS '09. WRI Global Congress on  (Volume:3 )

Date of Conference:

19-21 May 2009