28 search results - page 1 / 6 » The MAXQ Method for Hierarchical Reinforcement Learning |
ICML
1998
IEEE
14 years 5 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 5 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
13 years 6 months 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 4 months ago
2000
PKDD
2009
Springer
13 years 11 months ago
2009
Springer
Abstract. Innovations such as optimistic exploration, function approximation, and hierarchical decomposition have helped scale reinforcement learning to more complex environments, ...