We will be performing routine ERA maintenance starting 3PM Tuesday Feb 19 until 3PM Wednesday Feb 20. ERA searches and downloads will perform as usual, but the "Deposit" and "Edit" function will be suspended during the maintenance period. When the work is complete, we'll remove this notice. Thanks for your understanding!
SearchSkip to Search Results
- 1Actor-critic reinforcement learning algorithms
- 1Approximate dynamic programming
- 1Function approximation
- 1Policy gradient methods
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...