ICML
2010
IEEE
13 years 6 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 ...
CASSIS
2005
Springer
13 years 10 months ago
2005
Springer
This paper introduces notions of resource policy for mobile code to be run on smart devices, to integrate with the proof-carrying code architecture of the Mobile Resource Guarantee...