28 search results - page 1 / 6 » The MAXQ Method for Hierarchical Reinforcement Learning |
ICML
1998
IEEE
14 years 11 months ago
1998
IEEE
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
ICML
2001
IEEE
14 years 11 months ago
2001
IEEE
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...
IJCAI
2007
14 years 8 days ago
2007
Learning capabilities of computer systems still lag far behind biological systems. One of the reasons can be seen in the inefficient re-use of control knowledge acquired over the...
JAIR
2000
13 years 10 months ago
2000
PKDD
2009
Springer
14 years 5 months ago
2009
Springer
Abstract. Innovations such as optimistic exploration, function approximation, and hierarchical decomposition have helped scale reinforcement learning to more complex environments, ...