Sciweavers

2 search results - page 1 / 1
» Automatic Discovery of Subgoals in Reinforcement Learning us...
Sort
View
ICML
2005
IEEE
14 years 5 months ago
Identifying useful subgoals in reinforcement learning by local graph partitioning
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
Özgür Simsek, Alicia P. Wolfe, Andrew G....