Search
Skip to Search Results
Filter
Subject / Keyword
- 2Function approximation
- 2Temporal difference learning
- 2Two-timescale stochastic approximation
- 1Active learning
- 1Actor-critic methods
- 1Actor-critic reinforcement learning algorithms
Languages
Collections
Author / Creator / Contributor
Year
Item type
-
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 - 2 of 2