1233 search results - page 223 / 247 » Feudal Reinforcement Learning |
ICML
2010
IEEE
13 years 9 months ago
2010
IEEE
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
IIE
2007
13 years 8 months ago
2007
Conventional wisdom attributes the lack of effective technology use in classrooms to a shortage of professional development or poorly run professional development. At the same time...
ICRA
1994
IEEE
14 years 14 days ago
1994
IEEE
There is a close relationship between harmonic functions { which have recently been proposed for path planning { and hitting probabilities for random processes. The hitting probab...
ROBOCUP
2000
Springer
13 years 12 months ago
2000
Springer
Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to converge. This makes it difficult to be applied to re...
ESANN
2008
13 years 9 months ago
2008
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...