<--- Back to Details
| First Page | Document Content | |
|---|---|---|
 Date: 2010-01-22 02:08:08Smooth functions Distribution Functional analysis Universal property |
|
| First Page | Document Content | |
|---|---|---|
Date: 2010-01-22 02:08:08Smooth functions Distribution Functional analysis Universal property |
|
GQ(λ): A general gradient algorithm for temporal-difference prediction learning with eligibility traces Hamid Reza Maei and Richard S. Sutton Reinforcement Learning and Artificial Intelligence Laboratory, University of