Header logo is

Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning

2010

Article

ei


Most conventional policy gradient reinforcement learning (PGRL) algorithms neglect (or do not explicitly make use of) a term in the average reward gradient with respect to the policy parameter. That term involves the derivative of the stationary state distribution that corresponds to the sensitivity of its distribution to changes in the policy parameter. Although the bias introduced by this omission can be reduced by setting the forgetting rate γ for the value functions close to 1, these algorithms do not permit γ to be set exactly at γ = 1. In this article, we propose a method for estimating the log stationary state distribution derivative (LSD) as a useful form of the derivative of the stationary state distribution through backward Markov chain formulation and a temporal difference learning framework. A new policy gradient (PG) framework with an LSD is also proposed, in which the average reward gradient can be estimated by setting //!-- MFG_und--//amp;#947; = 0, so it becomes unnecessary to learn the value functions. We also test the performance of the proposed algorithms using simple benchmark tasks and show that these can improve the performances of existing PG methods.

Author(s): Morimura, T. and Uchibe, E. and Yoshimoto, J. and Peters, J. and Doya, K.
Journal: Neural Computation
Volume: 22
Number (issue): 2
Pages: 342-376
Year: 2010
Month: February
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
DOI: 10.1162/neco.2009.12-08-922
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@article{5904,
  title = {Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning},
  author = {Morimura, T. and Uchibe, E. and Yoshimoto, J. and Peters, J. and Doya, K.},
  journal = {Neural Computation},
  volume = {22},
  number = {2},
  pages = {342-376},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = feb,
  year = {2010},
  doi = {10.1162/neco.2009.12-08-922},
  month_numeric = {2}
}