Search
Skip to Search Results
Filter
Author / Creator / Contributor
Subject / Keyword
- 1Actor-critic reinforcement learning algorithms
- 1Approximate dynamic programming
- 1Bootstrapping
- 1Function approximation
- 1Natural-gradient
- 1Policy gradient methods
Collections
Year
Languages
Item type
Author: Bhatnagar, Shalabh
Author: Lee, Mark
Subject: Approximate dynamic programming
Subject: Bootstrapping
Subject: Function approximation
Subject: Policy gradient methods
Collections: Computing Science, Department of
Collections: Computing Science, Department of/Technical Reports (Computing Science)
-
2009
Bhatnagar, Shalabh, Sutton, Richard, Ghavamzadeh, Mohammad, Lee, Mark
Technical report TR09-10. We present four new reinforcement learning algorithms based on actor-critic, function approximation, and natural gradient ideas, and we provide their convergence proofs. Actor-critic reinforcement learning methods are online approximations to policy iteration in which...
1 - 1 of 1