Sciweavers

26 search results - page 6 / 6
» What Robots Can Do: Robot Programs and Effective Achievabili...
Sort
View
ATAL
2005
Springer
13 years 10 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson