|
|
| Record Number | 10233 |
| Reference Type | Journal Article |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2008 |
| Title | Natural actor critic |
| Journal/Conference/Book Title | Neurocomputing |
| Keywords | reinforcement learning, policy gradient, natural actor-critic, natural gradients |
Abstract |
In this paper, we suggest a novel reinforcement learning architecture, the Natural Actor-Critic. The actor updates are achieved using stochastic policy gradients em- ploying AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by lin- ear regression. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gra- dients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Empirical evaluations illustrate the effectiveness of our techniques in comparison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm.
|
| Notes | clmc |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-NC2008.pdf
|
| Volume | 71 |
| Number | 7-9 |
| Pages | 1180-1190 |
| Short Title | Natural actor critic |
| Papers are available as Adobe PDF ".pdf" files. Adobe Reader is available for free for all computer platforms.
|
|
|
|
|
Page last modified on August 10, 2006, at 06:47 PM
|
|
