Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

March 2016, Vol. 28, No. 3, Pages 563-593
(doi: 10.1162/NECO_a_00808)
© 2016 Massachusetts Institute of Technology
An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions
Article PDF (680.35 KB)
Abstract

We consider the learning problem under an online Markov decision process (MDP) aimed at learning the time-dependent decision-making policy of an agent that minimizes the regret—the difference from the best fixed policy. The difficulty of online MDP learning is that the reward function changes over time. In this letter, we show that a simple online policy gradient algorithm achieves regret for T steps under a certain concavity assumption and under a strong concavity assumption. To the best of our knowledge, this is the first work to present an online MDP algorithm that can handle continuous state, action, and parameter spaces with guarantee. We also illustrate the behavior of the proposed online policy gradient method through experiments.